search_skills

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

No annotations are provided, so the description carries the behavioral transparency burden. It makes clear this is a retrieval operation and that it returns match explanations, but it does not disclose pagination behavior, ordering, how structured filters combine, or any caveats around fields like external_skill_url or github_unreachable.

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

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

A single Chinese sentence conveys the action, resource, input modes, and output behavior with no wasted words. It is front-loaded around the core purpose and efficiently scannable.

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

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

With 11 input parameters, no annotations, and no per-parameter schema descriptions, the description is too sparse for an agent to call the tool confidently. It doesn't explain filter value formats, defaults, pagination, or special flag semantics, leaving too much to infer despite the existence of an output schema.

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

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, but it only gestures at 'structured conditions' without explaining any of the 11 parameters. The natural-language role of 'query' is implied, while limit, offset, stages, domains, methods, software, statuses, launch_only, external_skill_url, and github_unreachable are left entirely to their names.

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

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

The description names the specific verb '检索' (search), the resource '科学计算 Skills', the input modes (natural language + structured conditions), and the expected output (explain matching reasons). This clearly differentiates it from sibling tools like get_skill_card or get_skill_content, which retrieve specific skills.

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

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

The search-oriented phrasing implies it should be used for discovery when you don't have a specific skill, while siblings fetch individual skill details. However, there is no explicit when-to-use / when-not-to-use guidance or mention of alternatives, leaving routing mostly to inference.

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