Farm.js Docs

Search documentation

search_docs

Read-only

Search the docs by keyword with optional framework, version, package, and tag filters. Returns structured ambiguity and metadata warnings.

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
`tags`	No
`limit`	No
`query`	Yes
`cursor`	No	Opaque nextCursor from the preceding response page.
`locale`	No
`explain`	No	Include matched terms, scope decisions, ambiguity, and ranking reasons.
`package`	No
`version`	No
`audience`	No
`framework`	No

Output Schema

Name	Required	Description
`query`	Yes
`total`	Yes	Items in the complete filtered result set.
`format`	Yes
`filters`	Yes
`hasMore`	Yes	Whether another response page is available.
`results`	Yes
`audience`	Yes
`warnings`	Yes
`nextCursor`	No	Opaque cursor to pass as cursor on the next request.
`resultCount`	Yes	Items returned in this response page.
`indexGeneration`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

B3.2/5.0

Behavior3/5

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

readOnlyHint=true already establishes the safety profile, so the bar is lower. The description adds one genuinely useful behavioral detail - that results carry ambiguity and metadata warnings - but says nothing about pagination behavior, ranking, or result volume even though paging params exist.

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

Conciseness4/5

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

Two tight sentences that front-load the action and the filter list, then note the distinctive return behavior. No filler, though the second sentence could be more specific about what a 'metadata warning' means.

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

Completeness3/5

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

An output schema exists, so return values need not be spelled out, and the description reasonably covers the primary filter set. It is still thin for a 10-parameter search tool, omitting any mention of paging, the audience enum, or how limit interacts with results.

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 only 20% across 10 params, so the description must compensate. It names five filter dimensions (keyword, framework, version, package, tags) but is silent on limit, cursor, locale, audience, and explain, leaving half the surface undocumented in prose.

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?

States a specific verb and resource (search the docs by keyword) and enumerates the filter dimensions, so it is clearly a query tool rather than a lister. It stops short of naming how it differs from siblings like list_docs or list_search_facets.

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

Usage Guidelines2/5

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

The word 'search ... by keyword' implies the usage context but there is no explicit when-to-use, no condition selecting this over list_docs/list_search_facets, and no note on prerequisites. An agent must infer the routing itself.

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

All Farm.js Docs tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.