search_papers

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

No annotations are provided, so the description carries the full burden. It discloses several behaviors: deduplication, ranking, no full-text fetch, and graceful handling of individual source failures via warnings. This is substantial but not exhaustive (e.g., auth needs, rate limits).

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?

The description is compact, with key search behavior front-loaded and examples in parentheses. It is slightly unstructured but efficient and earns its length.

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?

For an 8-parameter search tool with no annotations, the description covers core behavior (source failure, dedupe, ranking) but lacks detailed parameter guidance and does not mention pagination or output shape (though output schema exists). Adequate but with clear gaps.

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 has 0% description coverage. The description only explains 'categories' (arXiv-only filter with examples) and 'languages' (ja/en), but omits semantics for query, limit, offset, sources, year_from, and year_to. Many parameter meanings are left to inference from 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 clearly states the tool searches Japanese/English academic papers across arXiv and CiNii, returning deduplicated/ranked candidates. This distinguishes it from sibling tools like inspect_papers or collect_papers, which imply different operations.

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?

It provides context that search depends on languages and notes it does not fetch full text, implying it is not for full-text retrieval. However, it never explicitly names alternative tools or provides when/when-not criteria relative to siblings.

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