---
slug: mcp-tool-search-cost
title: "MCP definitions use 10.6× more input tokens until tool search defers them"
kind: essay
status: published
hash: 93bb8b5ce458aee0afcf53db8e7bdf3864701202326cfcbb4775f8a2a699b2f7
created: 2026-07-26T03:31:41.249Z
updated: 2026-10-08T11:33:16.309Z
summary: "A live catalogue of 831 MCP tools measures 127,440 tokens of definitions; deferring them cut one measured turn from 149,187 input tokens to 14,109. The commands to measure your own, and the five filed cases where deferral leaves the bill in place."
tags: ["tooling","mcp","cost","tool-search","context-window","measurement"]
above: []
below: []
adjacent: []
nested: []
---
# MCP definitions use 10.6× more input tokens until tool search defers them

*A live catalogue of 831 MCP tools measures 127,440 tokens of definitions; deferring them cut one measured turn from 149,187 input tokens to 14,109. The commands to measure your own, and the five filed cases where deferral leaves the bill in place.*

A connected MCP server costs nothing while its tools sit idle, and costs on every request, because the definitions travel with the request. **MCP** — Model Context Protocol — is the wire format an agent uses to discover and call tools on an external server. Its discovery call, `tools/list`, returns one object per tool: a name, a description, and a JSON Schema for the arguments. A client that keeps those objects in the request pays for all of them every turn, whether the model calls one or none.

## Evidence status

**Observed** marks first-party measurements or runtime receipts from the named environment.
**Derived** marks arithmetic calculated from cited inputs. **Specified** marks vendor or standards
documentation. **Implemented** and **deployed** name code and live-state evidence, respectively.
**Reproduced** means the stated procedure was rerun. **Externally attested** marks operator reports;
those reports show that an experience occurred, not that it is universal.

## A definition is a name, a sentence and a schema, and the schema is the part that grows

One live tool object, from `POST https://miscsubjects.com/api/mcp` with `{"jsonrpc":"2.0","id":1,"method":"tools/list"}`:

```json
{
  "name": "CF_AI_GATEWAY_LIST_LOGS",
  "description": "List Logs MCP: https://ai-gateway.mcp.cloudflare.com/sse [fn · cf_ai_gateway]",
  "inputSchema": {
    "type": "object",
    "properties": {
      "gateway_id": { "type": "string", "description": "The gateway ID." },
      "page": { "default": 1, "type": "integer" },
      "per_page": { "default": 20, "type": "integer" },
      "order_by": { "default": "created_at", "type": "string",
        "enum": ["created_at","provider","model","model_type","success",
                 "cached","cost","tokens_in","tokens_out","duration","feedback"] },
      "order_by_direction": { "default": "desc", "type": "string", "enum": ["asc","desc"] },
      "start_date": { "type": "string" },
      "end_date": { "type": "string" },
      "feedback": { "type": "number" },
      "success": { "type": "boolean" },
      "cached": { "type": "boolean" },
      "model": { "type": "string" },
      "provider": { "type": "string" }
    },
    "required": ["gateway_id"]
  }
}
```

That object is **264 tokens** by the `o200k_base` tokenizer: 11 for the name, 22 for the description, 231 for argument names, types, defaults and one `enum` of eleven strings.

A description is written once by a human and stays a sentence. A schema grows with the API behind it — every optional filter, enum member and nested object — and nothing prunes it. The MCP specification requires it: `tools/list` returns `name`, optional `title`, `description` and `inputSchema` per tool, so there is no conforming way to publish a tool without publishing its argument surface.

Across the whole 831-tool catalogue on 2026-07-26, names cost 4,064 tokens, descriptions 54,596, schemas 54,465. Level in aggregate, which is not the folklore. Split by size and the folklore returns:

| Slice of the catalogue | Tools | Tokens | Share that is schema |
| --- | --- | --- | --- |
| Definitions under 300 tokens | 800 | 109,856 | 39% |
| Definitions 300 tokens or more | 31 | 17,584 | 67% |
| The 20 most expensive definitions | 20 | 13,963 | 75% |
| The single most expensive, `CF_OBSERVABILITY_QUERY_WORKER_OBSERVABILITY` | 1 | 1,803 | 95% |

Cheap tools are mostly prose; expensive tools are almost entirely schema. A catalogue's bill is set by its handful of query-shaped tools, not its median row. An independent measurement on a different server found the same tail: G-Core's MCP server at `GCORE_TOOLS=*` advertises 741 tools for about 488,013 tokens, an average of 659 per tool, one tool alone at about 7,046 tokens of schema.

## Measure it three ways, cheapest first

**1. `/context`, in a running session.** Breaks the window into system prompt, system tools, MCP tools, memory, skills and messages. Free, one second. Read the contradiction section before trusting a zero.

**2. The `usage` field of any API response.** Every Messages API response carries `usage.input_tokens`, `usage.output_tokens` and the cache counters. Send the same one-word prompt twice, with the servers attached and without, and subtract. The only method that measures what you are billed for.

**3. A capture server, for what the client puts on the wire.** A local HTTP server that speaks enough of the Messages API to answer, and logs every request:

```bash
git clone https://github.com/redacted/claude-code-cloudflare-gateway
cd claude-code-cloudflare-gateway
node tools/capture-gateway.mjs      # listens on :8787, appends capture.jsonl
```

It records `n_tools`, `tool_names`, `system_chars`, `system_cache_control`, `metadata` and the model per request, redacting `authorization` and `x-api-key`. Point the client at it twice, changing one variable:

```bash
ANTHROPIC_BASE_URL=http://localhost:8787 ANTHROPIC_AUTH_TOKEN=x \
  ENABLE_TOOL_SEARCH=false claude -p "say ok"

ANTHROPIC_BASE_URL=http://localhost:8787 ANTHROPIC_AUTH_TOKEN=x \
  ENABLE_TOOL_SEARCH=true claude -p "say ok"
```

Read the two tool counts out of the log:

```bash
python3 -c "
import json
for line in open('capture.jsonl'):
    r = json.loads(line)
    if r.get('n_tools') is not None:
        print(r['model'], 'tools=', r['n_tools'])
"
```

Two lines. On `claude-cli 2.1.165` against that server on 2026-07-25: `tools= 856` and `tools= 9` — the nine being `Agent`, `AskUserQuestion`, `Bash`, `Edit`, `Read`, `Skill`, `ToolSearch`, `Workflow`, `Write`.

**To price a catalogue without running the client**, count the tokens the server publishes. The command behind the 831-tool figures above, good against any HTTP MCP server that answers `tools/list`:

```bash
curl -s -X POST https://miscsubjects.com/api/mcp \
  -H "Authorization: Bearer $MCP_TOKEN" -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' -o tools.json

python3 -m venv /tmp/tokvenv && /tmp/tokvenv/bin/pip install tiktoken
/tmp/tokvenv/bin/python -c "
import json, tiktoken
enc = tiktoken.get_encoding('o200k_base')
t = json.load(open('tools.json'))['result']['tools']
tot = sum(len(enc.encode(json.dumps(x))) for x in t)
print('tools', len(t), 'tokens', tot, 'mean', round(tot/len(t), 1))
"
```

Output on 2026-07-26: `tools 831 tokens 127440 mean 153.4`, from a 434,636-byte response. `o200k_base` is OpenAI's tokenizer, not Anthropic's — treat it as a close estimate and billed `usage` as the truth. They agree to about 12% here: 149,187 billed input tokens for 856 definitions plus a system prompt and a short user message is 174.3 tokens per definition against the tokenizer's 153.4.

## Three configurations, same catalogue, same day

Same machine, same catalogue of 891 capabilities, same trivial prompt, `@cf/moonshotai/kimi-k2.7-code` through a Cloudflare AI Gateway, 2026-07-25. Tokens and cost read from the gateway's own log rows.

| Configuration | Tool definitions in the request | Input tokens | Cost per turn |
| --- | --- | --- | --- |
| Every directory row projected as an MCP tool, definitions in context | 856 | 149,187 | $0.02852109 |
| Same catalogue, `ENABLE_TOOL_SEARCH=true` | 9, one of them `ToolSearch` | 14,109 | $0.00443075 |
| No MCP server attached, the same 891 capabilities reached over HTTP | 9 built-in tools | 14,071 | $0.00456265 |

149,187 input tokens is 74.6% of a 200,000-token window, spent before the user's sentence is read. Deferring the definitions cuts that 10.6-fold, 135,078 tokens a turn.

The third row decides architecture: **tool search on is as cheap as having no MCP server at all** — 14,109 against 14,071, a 0.3% difference — with every tool still reachable. The tools were never the cost. The definitions were.

The dollar column is the gateway's own accounting and is an estimate; the token counts are measured at both ends and the argument rests on them.

That 14,071-token row is still readable. Fetched 2026-07-26 from the AI Gateway logs REST endpoint (`GET /accounts/<account_id>/ai-gateway/gateways/default/logs?per_page=3&order_by=created_at&order_by_direction=desc`):

```json
{"created_at":"2026-07-26T03:43:18.667Z","model":"@cf/moonshotai/kimi-k2.7-code",
 "metadata":{"via":"claude-code","shim":"api/aig","tools":9},
 "tokens_in":14071,"tokens_out":170,"cost":0.00456265,
 "usage_metadata":{"input_cached_tokens":12480}}
```

`metadata.tools` is what the client sent: nine, not 856, with the same catalogue attached.

## The attribution line was worth more than 12,000 cached tokens a turn

Claude Code prepends an attribution block — client version and prompt fingerprint — to the start of the system prompt. A prompt cache keys on an exact prefix, so a value that changes per request, at the front, means the prefix never matches and nothing before it is ever a hit. Anthropic's environment-variable reference: set `CLAUDE_CODE_ATTRIBUTION_HEADER` to `0` to omit the block, "Disabling it improves prompt-cache hit rates when routing through an LLM gateway. Caching on a direct connection to the Anthropic API is unaffected either way."

Measured on the rows above, cached input went from **64 tokens to 12,480 tokens** per turn once the line was dropped — 88% of a 14,109-token turn arriving from cache instead of priced as fresh.

```bash
export CLAUDE_CODE_ATTRIBUTION_HEADER=0
```

Anthropic's gateway protocol reference adds the version detail and the right place to fix it: from v2.1.181 the block is stable for the lifetime of a conversation behind a custom base URL, and "If your gateway must reshape system content, set `CLAUDE_CODE_ATTRIBUTION_HEADER=0` so Claude Code omits the block… omit it at the client rather than stripping or moving it in the gateway." Stripping it gateway-side breaks attribution downstream; omitting it at the client does not.

## Deferred tool search: names stay, schemas arrive on request

Anthropic's documentation describes the mechanism: "When tool search is active, tool definitions are withheld from the context window. The agent receives a summary of available tools and searches for relevant ones when the task requires a capability not already loaded. Up to five of the most relevant tools are loaded into context by default." A discovered tool stays available for later turns; if compaction removes it, the model searches again.

The switch:

```bash
export ENABLE_TOOL_SEARCH=true
```

Permanently, in `~/.claude/settings.json`:

```json
{ "env": { "ENABLE_TOOL_SEARCH": "true", "CLAUDE_CODE_ATTRIBUTION_HEADER": "0" } }
```

Every value the variable accepts:

| Value | Behaviour |
| --- | --- |
| unset | Deferred by default — but **loaded upfront** when `ANTHROPIC_BASE_URL` points at a non-first-party host, or on Google Cloud's Agent Platform |
| `true` | Always defer, and send the beta header even through a proxy. Requests fail on proxies that do not support `tool_reference` blocks |
| `auto` | Load upfront if the definitions fit within 10% of the context window, defer the overflow |
| `auto:N` | Same with a custom percentage, e.g. `auto:5` |
| `false` | Load every definition upfront, every turn |

Two costs come with it, both small. The search tool's own definition stays in the request — it is one of the nine measured above, and Anthropic's API reference is explicit that "At least one tool, normally the tool search tool itself, must stay non-deferred." And the first use of an unseen tool costs an extra round-trip; below roughly ten tools, loading everything upfront is faster.

The API-side mechanism differs from the client-side one in a way that matters if you are building a gateway. With `defer_loading: true` on the Messages API, "You still send every tool's full definition in the `tools` array on every request, including the deferred ones. The API needs them server-side to run the search." The saving there is context, not bytes. The capture above shows the client doing the other thing — sending nine definitions — because behind a non-first-party base URL Claude Code resolves the search itself. Both are called tool search. Only one shrinks what leaves your machine.

## Five ways the definitions stay in the bill anyway

| What still costs | Where it was observed | The report |
| --- | --- | --- |
| First-party servers exempt from deferral | Claude Desktop, `anthropics/claude-code` issue 76372, 2026-07-10 | With tool search active, third-party MCP tools defer to names only, but "three Desktop built-in servers load complete schemas upfront every session" — about 3,900 tokens with no opt-out, isolated by reading `message.usage` from session JSONL across 6 sessions |
| Servers invisible to the search index | Claude Code 2.1.114, `anthropics/claude-code` issue 57033, 2026-05-07 | Servers added at claude.ai/settings/connectors show Connected in `/mcp`, yet "Any `ToolSearch` query that should match a claude.ai MCP tool returns zero results". Local `.mcp.json` and plugin servers index fine |
| Threshold computed from the wrong model | `hermes-agent` issue 57520, 2026-07-03 | The auto-gate reads the configured default model, not the session model, so "the gate is scaled to the wrong window" — a 98,304-token local model gets a 25,600-token threshold derived from a 256K cloud model instead of 9,830, and takes the whole payload inline |
| A turn that silently completes empty | codex-cli 0.133.0, `openai/codex` issue 24536, 2026-05-26 | "`codex exec` can silently finish with no assistant message when an explicitly configured MCP tool is deferred behind `tool_search`" — the server stays healthy and registered but is only reachable through deferral, and the harness accepts the empty turn |
| Lazy loading invalidating the prompt cache | Hacker News, 2026-03-01 | "The main problem with this approach at the moment is it busts your prompt cache, because LLMs expect all tool definitions to be defined at the beginning of the context window" |

The cache row cuts the other way for the deferred case. Anthropic's caching page puts tool definitions in the system-prompt layer, so the cache invalidates when the set of definitions changes between turns — but with deferred tools, "a server connecting, disconnecting, or changing its tool list only appends new content and doesn't disturb anything already cached", while with tools in the prefix "any change to them invalidates the cache". A gateway is named as one place where deferral is off and the prefix is therefore fragile: a stdio process exiting, an HTTP session expiring or an automatic reconnect invalidates the whole cached prefix with nobody touching a keyboard.

An operator who ran it and was not convinced, on Hacker News on 2026-03-15: "And no, the tool search function recently introduced by Anthropic does not completely solve this problem."

## One harness reports zero tokens per tool. Others publish tables of tens of thousands

Zero, filed against Claude Code as issue 23228 on 2026-02-05: "When running the `/context` command to check token usage, the output includes a long list of all MCP tool definitions (28 in my case), each showing '0 tokens'."

Not zero, filed on 2026-03-01 with a per-server breakdown: "The main agent context burns 16.9k tokens (8.5% of 200k) loading 68 MCP tool schemas at session start. Most are never called by the main agent — they're used by subagents." That author's table attributes 6.0k to one server's 25 tools, 3.3k to another's 14. Two more, independently: 741 tools at about 488,013 tokens on a G-Core server, and 250-plus definitions across 9 servers at "~40,000-70,000 tokens of tool definitions loaded upfront".

Both can be true, and the mechanism is documented. `/context` reports what is **in the context window**, category by category. Deferred definitions are by construction not in the window — Anthropic's cost guidance: "MCP tool definitions are deferred by default, so only tool names enter context until Claude uses a specific tool." A per-tool row of `0 tokens` is then accurate, and the residual cost lands under another heading. The tables of tens of thousands come from sessions where the definitions were not deferred — an older client, a `false` setting, a non-first-party base URL, `alwaysLoad`, an exempt built-in server — and from harnesses that count the catalogue rather than ask the client.

Which to trust for a decision: **neither, over the `usage` field of your own responses.** `/context` reports placement, not billing, and its zero is silent about the 3,900 tokens of exempt built-in schemas in issue 76372. A tokenizer table reports the size of a catalogue, not what your client chose to send — the capture above shows a client sending 9 of 856. Only `usage.input_tokens`, differenced across two otherwise identical runs, answers the question being asked.

One dissent earns its place, from Hacker News on 2026-05-30: "The idea that MCP tool definitions take up a certain number of tokens is laughable. That's an implementation detail of the agent harness." Correct about the protocol, beside the point about the invoice: the protocol mandates no loading strategy, and the client you are running has already picked one and is billing you for it.

## The arithmetic at 200 turns a day

200 model turns in a working day, 30 days in a month. Substitute your own turn count; the multiplication is the same.

| Configuration | Cost per turn | × 200 turns = per day | × 30 days = per month |
| --- | --- | --- | --- |
| 856 definitions in every request | $0.02852109 | $5.70 | $171.13 |
| `ENABLE_TOOL_SEARCH=true` | $0.00443075 | $0.89 | $26.58 |
| No MCP server, capabilities over HTTP | $0.00456265 | $0.91 | $27.38 |

One environment variable is worth $4.82 a day and **$144.54 a month** on one machine, one catalogue, these rates. In tokens, which do not depend on anyone's pricing: 135,078 fewer input tokens per turn, 27,015,600 fewer per day.

Two effects the table does not price. The definitions occupied 74.6% of a 200,000-token window, so the ceiling on what a session can hold moves further than the invoice does. And tool-selection accuracy is documented to degrade "with more than 30-50 tools loaded at once" — a quality cost with no line item.

## Five responses, ranked by what they cost you to adopt

**1. Turn tool search on.** One variable, no code, every tool still reachable, measured 10.6× fewer input tokens. Trade-off: an extra round-trip on first use of an unseen tool; unavailable behind a base URL that cannot forward `tool_reference` blocks; below ten tools it is slower than loading them.

**2. Scope servers per project.** Enable a server only in the repository that needs it. An operator on Hacker News, 2026-07-12: "I enable tools specific to each project only in that project, and have very very few in my global config. Like <5k tokens worth." Trade-off: manual, and it fails the way manual hygiene always fails — the day you forget.

**3. Collapse many tools into few.** Replace N tools with one or two that take a name and arguments and dispatch internally. From the operator who built it: "This basically takes your APIs, databases, and docs and compresses them into 2 MCP tools (~1,000 tokens) instead of N tools (100K+ tokens)." A minimal version of the same idea, reported at about 60 tokens: one bare tool with a one-line description that unlocks the rest when called. Trade-off: you have rebuilt tool search without the harness's search quality, and the model must learn your dispatch convention.

**4. Take the catalogue out of the prompt entirely.** Publish capabilities behind an HTTP contract the model reads on demand, keep only the built-in tools. Measured at 14,071 input tokens with 891 capabilities reachable — the same number as tool search, a different structure, because catalogue size is no longer a term in the per-turn equation and no host support is required. Trade-off: your capabilities are not MCP tools, so anything that consumes MCP does not see them. Dimension by dimension in [Tool search versus a catalogue as data](/a/tool-search-vs-catalogue-as-data), the data layer in [Tooling as data](/a/tooling-as-data), the three exposures side by side in [MCP as a projection](/a/mcp-as-a-projection).

**5. Do nothing.** Defensible at a small tool count: under about ten tools, upfront loading is faster and the search round-trip is pure overhead. At 150–200 tools, two reports show the limit: one one-word prompt produced a request with "`prompt_tokens: 154,367`"; in the other, roughly 200 tool schemas exceeded a 32k window so completely that "`/compact` succeeded in producing a summary, but the very next request still failed."

## Symptom, cause, fix

| Symptom | Cause | Fix |
| --- | --- | --- |
| Input tokens in the tens of thousands before your first word | Every definition in the prefix, every turn | `ENABLE_TOOL_SEARCH=true` |
| Setting it changed nothing, tools still all loaded | `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` is set — it "keeps tool search off, and `ENABLE_TOOL_SEARCH` can't override it" | Unset it, or accept upfront loading |
| Request fails after enabling it, behind a proxy | The proxy does not forward `tool_reference` blocks; errors of the form "Unexpected value(s) for the `anthropic-beta` header" or "Extra inputs are not permitted" | Fix the proxy to pass the beta header through, or set `ENABLE_TOOL_SEARCH=false` |
| Deferred by default on a direct connection, upfront through a gateway | Deferral is off by default "when `ANTHROPIC_BASE_URL` points to a non-first-party host" | Set `ENABLE_TOOL_SEARCH=true` explicitly |
| Tool search finds nothing for a server that `/mcp` shows Connected | claude.ai-hosted connectors are not in the search index (issue 57033) | Add the server via local `.mcp.json` instead |
| A scripted run ends with no assistant message | The required tool was deferred and the harness accepted an empty turn (codex issue 24536) | Mark that server `alwaysLoad`, or pin it non-deferred |
| One server must never need a search step | Deferral applies to every server by default | `"alwaysLoad": true` on that server in `.mcp.json` — every one of its tools then loads at session start regardless of `ENABLE_TOOL_SEARCH` |
| Cached input near zero behind a gateway | The attribution block changes the prefix per request | `CLAUDE_CODE_ATTRIBUTION_HEADER=0` at the client, never stripped in the gateway |
| Cache misses mid-session for no visible reason | A server connected, disconnected or pushed a tool-list change while definitions sat in the prefix | Defer the tools, so a server change "only appends new content" |
| `/context` shows every MCP tool at 0 tokens | Deferred definitions are not in the window; `/context` reports placement, not billing | Difference `usage.input_tokens` across two runs instead |
| Tool search on and the bill barely moved | Built-in or `alwaysLoad` servers are exempt (issue 76372, about 3,900 tokens) | Audit with a capture server; `n_tools` in the log is the ground truth |

The gateway that produced these log rows, and how the same client runs on a non-Anthropic model, is documented in [Claude Code on Kimi, GLM or Grok through your own Cloudflare account](/a/claude-code-on-cloudflare-ai-gateway).

## Facts

```json
{
  "converted_from": "markdown",
  "original_updated": "2026-07-26T05:37:33.294Z",
  "register": "essay",
  "category": null
}
```

## Sources

1. [Claude Code environment variables — ENABLE_TOOL_SEARCH and CLAUDE_CODE_ATTRIBUTION_HEADER](https://code.claude.com/docs/en/env-vars) — “Set to `0` to omit the attribution block (client version and prompt fingerprint) from the start of the system prompt. Disabling it improves prompt-cache hit rates when routing through an LLM gateway. Caching on a direct connection to the Anthropic API is unaffected either way” (sha256 79baf0b5dfc662cb)
2. [Connect Claude Code to tools via MCP — scale with MCP tool search](https://code.claude.com/docs/en/mcp) — “Tool search keeps MCP context usage low by deferring tool definitions until Claude needs them. Only tool names and server instructions load at session start, so adding more MCP servers has minimal impact on your context window.” (sha256 ce0faf966a9ee84b)
3. [How Claude Code uses prompt caching — what invalidates a cached prefix](https://code.claude.com/docs/en/prompt-caching) — “Deferred tools, the default on supported models: a server connecting, disconnecting, or changing its tool list only appends new content and doesn’t disturb anything already cached. Tools loaded into the prefix: any change to them invalidates the cache. This happens when tool search is unavailable or disabled, such as on Google Cloud’s Agent Platform or with a custom ANTHROPIC_BASE_URL gateway.” (sha256 6364b6d42d93a79a)
4. [Gateway protocol reference — where to disable the attribution block](https://code.claude.com/docs/en/llm-gateway-protocol) — “If your gateway must reshape system content, set `CLAUDE_CODE_ATTRIBUTION_HEADER=0` so Claude Code omits the block. Anthropic and the cloud providers’ Claude endpoints read the block for attribution, so omit it at the client rather than stripping or moving it in the gateway.” (sha256 cba7f7b38ef6d574)
5. [Manage costs effectively — MCP tool definitions are deferred by default](https://code.claude.com/docs/en/costs) — “MCP tool definitions are deferred by default, so only tool names enter context until Claude uses a specific tool. Run `/context` to see what’s consuming space.” (sha256 1296ff8f74b697a6)
6. [Debug your configuration — what /context actually reports](https://code.claude.com/docs/en/debug-your-config) — “The `/context` command shows everything occupying the context window for the current session, broken down by category: system prompt, system tools, MCP tools, custom subagents with the source each loaded from, memory files, skills, and conversation messages.” (sha256 fceea1e9ce837d4f)
7. [Scale to many tools with tool search — the mechanism and its break-even point](https://code.claude.com/docs/en/agent-sdk/tool-search) — “When tool search is active, tool definitions are withheld from the context window. The agent receives a summary of available tools and searches for relevant ones when the task requires a capability not already loaded. Up to five of the most relevant tools are loaded into context by default.” (sha256 ad73117df68f2878)
8. [Model Context Protocol specification — tools/list](https://modelcontextprotocol.io/specification/2025-06-18/server/tools) — “{ "name": "get_weather", "title": "Weather Information Provider", "description": "Get current weather information for a location", "inputSchema": { "type": "object", "properties": { "location": { "type": "string", "description": "City name or zip code" } }, "required": ["location"] } }” (sha256 ebc7e877dd1fe80e)
9. [Tool search tool — defer_loading controls context, not the request body](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) — “You still send every tool’s full definition in the `tools` array on every request, including the deferred ones. The API needs them server-side to run the search and expand `tool_reference` blocks.” (sha256 6e292728f433c3e8)
10. [capture-gateway.mjs — the logging server behind these wire measurements](https://github.com/redacted/claude-code-cloudflare-gateway) — “tools/capture-gateway.mjs — a local Anthropic-compatible server that logs every request, recording n_tools, tool_names, system_chars, system_cache_control and metadata, with authorization and x-api-key redacted” (sha256 05246178679fe558)
11. [tiktoken harness against a live MCP server: 741 tools, ~488,013 tokens](https://github.com/G-Core/gcore-mcp-server/issues/14) — “with `GCORE_TOOLS=*` it advertises **741 tools / ~488,013 tokens** (659/tool) — that exceeds a 200K context window on its own, so the full config can’t actually be used with most models.” (sha256 bd4c02e46be22e9d)
12. [/context shows 28 MCP tool definitions, each at 0 tokens](https://github.com/anthropics/claude-code/issues/23228) — “When running the `/context` command to check token usage, the output includes a long list of all MCP tool definitions (28 in my case), each showing "0 tokens".” (sha256 512bb6d386de1a11)
13. [16.9k tokens on 68 MCP tool schemas, broken down per server](https://github.com/yonatangross/orchestkit/issues/885) — “The main agent context burns **16.9k tokens (8.5% of 200k)** loading 68 MCP tool schemas at session start. Most are never called by the main agent — they’re used by subagents.” (sha256 9771c534bc4f415f)
14. [9 MCP servers, 250+ definitions, 40-70k tokens on every message](https://github.com/anomalyco/opencode/issues/35376) — “With 9 MCP servers connected (project-tools, supabase, agent-browser, chrome-devtools, playwright, memory, context7, sequential-thinking, fetch), this results in ~40,000-70,000 tokens of tool definitions loaded upfront” (sha256 dba5274df446b2f1)
15. [Built-in servers load full schemas despite tool search — ~3.9k tokens, no opt-out](https://github.com/anthropics/claude-code/issues/76372) — “With tool search active (`ENABLE_TOOL_SEARCH` unset), third-party MCP tools correctly defer to names-only. But three Desktop built-in servers load complete schemas upfront every session” (sha256 61f8a25cf0a92429)
16. [ToolSearch does not index claude.ai-hosted servers](https://github.com/anthropics/claude-code/issues/57033) — “the `ToolSearch` deferred-tool discovery mechanism does NOT include them in its index. Any `ToolSearch` query that should match a claude.ai MCP tool returns zero results” (sha256 eff1fce034d8afbf)
17. [A deferred tool can end a scripted run with no assistant message](https://github.com/openai/codex/issues/24536) — “`codex exec` can silently finish with no assistant message when an explicitly configured MCP tool is deferred behind `tool_search`.” (sha256 e1b5ba624c1129b4)
18. [The deferral threshold is computed from the wrong model](https://github.com/NousResearch/hermes-agent/issues/57520) — “For any session running a model *other than* the configured default (e.g. `--model qwen3.6-27b --provider llamacpp`, or a model switched via `/model` in the TUI), the gate is scaled to the wrong window.” (sha256 424c64f52637f7f9)
19. [Loading tools lazily busts the prompt cache](https://news.ycombinator.com/item?id=47209810) — “The main problem with this approach at the moment is it busts your prompt cache, because LLMs expect all tool definitions to be defined at the beginning of the context window.” (sha256 52099c72c3c160d3)
20. [A first-hand verdict: tool search does not completely solve it](https://news.ycombinator.com/item?id=47392361) — “And no, the tool search function recently introduced by Anthropic does not completely solve this problem.” (sha256 686b8b569e20ca67)
21. [The dissent: token cost is a harness detail, not a protocol property](https://news.ycombinator.com/item?id=48331540) — “The idea that MCP tool definitions take up a certain number of tokens is laughable. That’s an implementation detail of the agent harness.” (sha256 6e878cf685c8fe62)
22. [The positive report: deferral retired the context-bloat complaint](https://news.ycombinator.com/item?id=48332962) — “Because Claude Code only loads the tools it needs now, so context bloat is pretty much solved for MCPs.” (sha256 30fdfb8240fef6f2)
23. [Per-project scoping keeps a global tool surface under 5k tokens](https://news.ycombinator.com/item?id=48885036) — “I enable tools specific to each project only in that project, and have very very few in my global config. Like <5k tokens worth.” (sha256 fc631e09f48b1c70)
24. [Collapsing an API into two MCP tools: 100K+ tokens down to ~1,000](https://news.ycombinator.com/item?id=47614267) — “This basically takes your APIs, databases, and docs and compresses them into 2 MCP tools (~1,000 tokens) instead of N tools (100K+ tokens). Claude was burning tokens (and a lot of them for me) on just tool definitions.” (sha256 ebc299379fd9d888)
25. [A hand-rolled gate tool at about 60 tokens](https://news.ycombinator.com/item?id=47719249) — “That first tool consumes only about 60 tokens. As long as the LLM doesn’t need the tools, it takes almost no space.” (sha256 f772b4396a411d48)
26. [A unified-API vendor measured 50,000+ tokens before the first user message](https://news.ycombinator.com/item?id=47400262) — “We built a unified API with a large surface area and ran into a problem when building our MCP server: tool definitions alone burned 50,000+ tokens before the agent touched a single user message.” (sha256 c5dc7811fd6f0da1)
27. [One popular server named at about 50k tokens](https://news.ycombinator.com/item?id=45955033) — “Right now loading GitHub MCP takes something like 50k tokens.” (sha256 5a53dcb41f603324)
28. [A one-word prompt that cost 154,367 input tokens](https://github.com/nimbalyst/nimbalyst/issues/914) — “A one-word prompt ("Reply with exactly one word: pong") produced a request with `prompt_tokens: 154,367`” (sha256 b062162e927fe2ef)
29. [Schema overhead that /compact cannot recover](https://github.com/ruvnet/ruflo/issues/2726) — “`/compact` succeeded in producing a summary, but the **very next request still failed** — the non-compactable overhead (system prompt + ruflo tool schemas + plugin agent/skill listings) alone exceeded the limit.” (sha256 38e199d89ef98d32)
30. [First-party: 831 published tool definitions, 127,440 tokens](https://miscsubjects.com/a/mcp-tool-search-cost) — “tools 831 tokens 127440 mean 153.4 — from a tools/list response of 434,636 bytes; names 4,064 tokens, descriptions 54,596, schemas 54,465” (sha256 5d95ee2801323009)
31. [First-party: one real definition, 264 tokens, and where the tokens sit](https://miscsubjects.com/a/mcp-tool-search-cost) — “CF_AI_GATEWAY_LIST_LOGS = 264 tokens: 11 name, 22 description, 231 schema. Across the catalogue, the 20 most expensive definitions are 13,963 tokens and 75% schema; the single most expensive, CF_OBSERVABILITY_QUERY_WORKER_OBSERVABILITY, is 1,803 tokens and 95% schema.” (sha256 e3a3884d7fc61dfa)
32. [First-party: a gateway log row, nine tools, 14,071 input tokens](https://developers.cloudflare.com/ai-gateway/observability/logging/) — “{"created_at":"2026-07-26T03:43:18.667Z","model":"@cf/moonshotai/kimi-k2.7-code","metadata":{"via":"claude-code","shim":"api/aig","tools":9},"tokens_in":14071,"tokens_out":170,"cost":0.00456265,"usage_metadata":{"input_cached_tokens":12480}}” (sha256 10f3d57f7b8db028)
33. [First-party: 856 definitions become 9 on the wire](https://github.com/redacted/claude-code-cloudflare-gateway) — “ENABLE_TOOL_SEARCH=false tools=856  |  ENABLE_TOOL_SEARCH=true tools=9 [‘Agent’,‘AskUserQuestion’,‘Bash’,‘Edit’,‘Read’,‘Skill’,‘ToolSearch’,‘Workflow’,‘Write’]” (sha256 56bcf4ee321375da)
34. [First-party: three configurations priced from gateway log rows](https://miscsubjects.com/a/mcp-tool-search-cost) — “856 definitions 149,187 input / $0.02852109 · tool search on 14,109 / $0.00443075 · no MCP server, 891 capabilities over HTTP 14,071 / $0.00456265” (sha256 1c6db8986b3edf49)