参考文献

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

Adds dedup rules and data source priorities beyond annotations (readOnlyHint=true). Discloses behavioral traits like '智能去重' (smart dedup) but doesn't cover all behaviors (e.g., pagination).

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?

Concise yet comprehensive: one sentence for purpose, bulleted parameter list, and notes on data sources and dedup. No filler, every sentence adds value.

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?

Covers parameters and behavioral rules well, but lacks description of return format or example. For a reference-listing tool without output schema, a brief note on output structure would improve completeness.

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?

With 0% schema description coverage, the description fully explains each parameter: identifier types, id_type enum, sources defaults, max_results range, include_metadata purpose. Adds meaning beyond the plain schema.

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?

Description clearly states '获取参考文献工具' (get references tool) and specifies it retrieves references for a given identifier with dedup. It is distinct from siblings like get_article_details or search_literature.

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?

Implied usage through parameter descriptions, but no explicit when-to-use or when-not-to-use compared to siblings. The dedup rules and data sources provide context but not direct alternatives.

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