unity-api-mcp

search_unity_api

Find accurate Unity API classes, methods, properties, and fields by keyword; returns ranked summaries to prevent hallucinated signatures and deprecated usage.

Instructions

Search Unity API documentation by keyword.

Use this to find Unity classes, methods, properties, and fields. Returns ranked results with summaries.

Args: query: Search terms (e.g. "Physics Raycast", "SceneManager load", "Transform position") n_results: Max results to return (default 5, max 20) member_type: Optional filter — "type", "method", "property", "field", or "event"

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_unity_api"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes
`n_results`	No
`member_type`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.1.1Oct 16, 2026

TDQS

A3.6/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden, but this is a low-risk read operation and it does disclose that results are ranked and include summaries. It omits anything about indexing scope, freshness, or empty-result behavior. Since an output schema exists, the return shape need not be spelled out, keeping this at an adequate 3.

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?

Front-loaded with the purpose, then the usage line, then a tight Args block. Every line contributes, and the parameter lines earn their space by carrying enum/limit information absent from the schema.

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?

For a 3-parameter read-only search with an output schema already describing the response, the description covers purpose, usage, and all parameter meanings. A note on exact vs keyword matching or result ordering would close the last gap.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate and it largely does: it adds example queries, the "max 20" bound on n_results (the schema only shows default 5), and the enumerated member_type values ("type", "method", "property", "field", "event") that the schema lacks entirely. Only the exact matching semantics of query are left unstated.

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 ("Search") and resource ("Unity API documentation") plus the object domain (classes, methods, properties, fields). It does not explicitly name or contrast against siblings like get_class_reference or get_method_signature, so an agent must infer that this is the keyword-discovery path versus their name-lookup path.

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?

"Use this to find Unity classes, methods, properties, and fields" implies usage (discovery when you don't have an exact identifier) but never states when to prefer it over the get_* siblings or any exclusions. Enough to orient, not enough to route decisively.

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

Deploy Server