search_papers

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

With no annotations, the description carries the full burden. It discloses that no API keys are needed, specifies per-source result limits (1-25 arXiv / 1-20 Crossref), describes the return fields (id/url/pdf_url/title/authors/summary/published), and mentions the error return format. It also notes that pdf_url is optional (indicated by the '?' in the return example). This is strong, though it could explicitly state the operation is read-only and has no side effects.

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 well-structured with a heading, a bulleted Args list, and a Returns section. Every sentence carries useful information: examples, default values, and a downstream workflow hint. It front-loads the purpose and keeps the details organized, with no filler or repetition.

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?

The description is complete for a 4-parameter tool. It covers all parameters, provides return format details, notes the error case, and suggests an integration with the 'document' tool. Given the existing output schema (not shown but present), the description does not need to repeat return values, and it supplies enough for an agent to call it correctly.

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 fully compensates. It explains each parameter: query with an example ('transformer attention scaling laws'), limit with per-source ranges, source with defaults and meanings ('arxiv' for preprints, 'crossref' for DOI-backed), and category with an example format ('cs.LG'). This adds significant meaning beyond the bare schema, making parameters self-explanatory.

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's purpose: 'Search academic papers via arXiv or Crossref — no API keys.' This is a specific verb (search) and resource (academic papers) with two named sources, and it naturally distinguishes from siblings like the general 'search' tool or 'document' for extraction. The mention of specific sources and the absence of API keys adds clarity.

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 provides clear context for when to use this tool: when searching academic papers via arXiv or Crossref. It also gives a workflow hint by suggesting to feed the returned pdf_url into the 'document' tool for full-text extraction. However, it does not explicitly state when not to use it or compare with alternatives like 'search' or 'deep_research', so it falls slightly 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.