Claude Platform Docs

Search docs

search_docs

Read-onlyIdempotent

Search Claude documentation (the guides and the API reference together) by keyword or phrase. Returns matching pages and API endpoints ranked by relevance, with snippets showing context around matches.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_docs"
  }
}

Input Schema

Name	Required	Description
`kind`	No	Only return results of one kind: "prose_page" (guide pages), "api_sdk_method" (one API method, such as "Create a Message"), or "api_sdk_resource" (a group of endpoints, such as Messages).
`limit`	No	Maximum results to return (default: 10, max: 50)
`query`	Yes	Search query (keywords or phrase)
`sdk_language`	No	Search this SDK's API reference together with the guides. Accepts an SDK language such as "python" or "typescript", or "http" (default — the language-neutral REST reference); unrecognized values fall back to "http". Results for endpoints then link to that SDK's reference pages and match its method names.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already establish read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful return behavior: matching pages and API endpoints ranked by relevance with context snippets, which helps set expectations beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two front-loaded sentences with no wasted language. It states the action, scope, and return shape immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description helpfully explains what is returned and how results are ranked. Annotations cover safety, and the schema covers parameters, so the remaining gap is minor, mainly the absence of explicit sibling routing guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents query, kind, limit, and sdk_language thoroughly. The description adds only the high-level idea of searching guides and API reference together, without meaningfully extending parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: "Search Claude documentation (the guides and the API reference together) by keyword or phrase." It clearly distinguishes search from retrieval siblings like get_doc and get_api_endpoint conceptually, though it does not name those alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by "by keyword or phrase," but the description does not explicitly say when to use this instead of get_doc, get_api_endpoint, or get_navigation. It lacks named alternatives and exclusions, leaving the agent to infer the routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Claude Platform Docs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?