search_papers

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

Annotations indicate readOnlyHint=true, and the description aligns by stating this is a search operation. It goes beyond annotations by disclosing arXiv rate limiting (~3s between requests), retry behavior for transient 429/503 errors, persistent rate limits returning status=rate_limited, and pagination behavior via next_start. It also documents default abstract_mode and truncation behavior.

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 dense but well-organized, with key behavioral details front-loaded. It covers many aspects (syntax, categories, dates, sorting, defaults, pagination, rate limits) without excessive verbosity. Some details like the rate-limit note could arguably be moved to a 'Notes' section, but overall it's efficiently structured and every sentence provides actionable information.

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 the tool has 8 parameters, no output schema, and a rich behavioral profile, the description is quite complete. It covers query construction, pagination, result metadata fields, and error/rate-limit behavior. It doesn't explicitly describe the full response shape beyond those fields, but given the lack of an output schema, this is a minor gap. The description leaves little room for an agent to call incorrectly.

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 100%, so all parameters are individually documented. The tool description adds value beyond the schema by explaining the overall query behavior (unprefixed terms match title+abstract, not authors) and by reinforcing the pagination contract (pass next_start with same abstract_mode). The description doesn't introduce new parameter dimensions but meaningfully supplements the 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?

The description clearly states the tool's function: searching arXiv by query with optional filters and pagination. It explicitly covers the search syntax, categories, date range, sorting, and output controls. This distinguishes it from sibling tools like semantic_search, get_abstract, and list_papers, which serve different retrieval purposes.

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 explicit usage guidance including query syntax tips (prefer quoted phrases, field prefixes), category recommendations, date format expectations, and default/limit values. It also directs use of get_abstract after compact search rather than after abstract_mode=full, giving clear when-to-use context. Sibling differentiation is implicit through this comprehensive guidance.

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