arxiv_paper_search_by_query

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

No annotations are provided, so the description must carry the behavioral burden. The description discloses that the query is passed verbatim, that field prefixes are supported, and that a bare title yields a loose full-text search. This adds valuable behavioral context beyond the schema. However, it does not mention any side effects (likely none for a read-only search), authentication needs, rate limits, or what the output format looks like (no output schema exists). The description is not misleading, but it leaves several behavioral aspects undisclosed.

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 concise and well-structured. It opens with a clear purpose statement, then immediately provides actionable details about query construction, including examples and a caveat. Every sentence adds value; there is no redundancy or fluff. The critical usage information is front-loaded, and the warning about bare titles is placed at the end to avoid distraction.

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?

Given that there is no output schema and only two parameters, the description should explain what the tool returns and how to interpret results. It does not mention the return format, pagination, or how results are ordered. It also does not explain how `max_results` affects the response. The description is strong on query semantics but incomplete on output expectations and parameter effects, leaving an agent to guess at the result structure.

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 coverage is 0%, so the description must compensate for both parameters. The description thoroughly explains the `query` parameter: it is passed verbatim, field prefixes work, and examples are given. This is excellent. However, `max_results` is not mentioned at all; its meaning is left to inference from the name and default value. Since the description covers only half of the parameters, it partially compensates for the lack of schema descriptions.

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 'Search for papers in ArXiv using a query string.' This is a specific verb ('search') and resource ('papers in ArXiv'), and it distinguishes the tool from sibling search tools (e.g., pubmed_paper_search_by_query) by explicitly naming ArXiv. It also contrasts with arxiv_paper_detail_by_id, which is for detail retrieval by ID, and arxiv_latest_paper_list_by_category, which is category-based listing.

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 description gives concrete usage guidance: it explains that the query is passed verbatim to arXiv and that field prefixes (ti:, au:, abs:, cat:) can be used to pinpoint a specific paper. It also warns that a bare title is a loose full-text query and may not reliably return the paper. This is helpful for an agent to decide how to construct queries. However, it does not explicitly compare to alternative search tools (e.g., when to use this vs. a Scopus query) or state when not to use this tool, so it falls short of full guidance.

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