Skip to main content
Glama

搜索能力

cocos_capability_search
Read-only

Search Cocos Creator operations and capabilities by query or module to find the right action before executing long-tail features; supports project scoping and pagination.

Instructions

搜索操作目录;先查询再执行长尾功能

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cocos_capability_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNo
moduleNo
offsetNo
projectIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / projectId
      Added value: +{
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

C2.6/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the bar is lower. Beyond that the description discloses nothing: not what the results look like, not how paging via limit/offset behaves, and not that the returned identifiers are what feed into cocos_capability_execute.

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

Conciseness3/5

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

Two short clauses, front-loaded with the action and followed by the workflow hint, with no filler. The problem is under-specification rather than verbosity, so the efficiency is real but the brevity costs information an agent needs.

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

Completeness2/5

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

For a five-parameter entry-point tool with no output schema and no parameter documentation, the description is too thin. It omits the pagination contract, the shape of results, and the hand-off to cocos_capability_describe/execute, which is the whole reason a search step exists in this catalog-plus-execute pattern.

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

Parameters2/5

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

Schema description coverage is 0% across five parameters, so the description bears the full explanatory burden and does not meet it. It only vaguely implies a search term for "query"; module, projectId, limit and offset receive no meaning at all, leaving the agent to guess whether module is a filter key or a namespace.

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

Purpose3/5

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

"搜索操作目录" gives a recognisable verb (search) plus resource (operation/capability catalog), which is more than a restatement of the name. However, it never names the closely related siblings cocos_capability_describe and cocos_capability_execute, so the boundary between searching, describing and executing is left for the agent to infer from tool names alone.

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?

"先查询再执行长尾功能" does encode an ordering rule: search first, then run less-common functionality. That is genuinely useful implied guidance, but there are no explicit exclusions, no statement that cocos_capability_execute is the follow-up step, and no note on whether known capabilities can skip the search.

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