search_docs

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

With no annotations, the description carries the full burden of disclosing behavior. It explains the difference in results between UAT and bot identity, mentions that the response carries viaUser, and details pagination with hasMore/nextOffset. This is valuable behavioral context. It doesn't mention rate limits or error handling, but for a search tool the key behaviors are covered. No contradiction with annotations exists since none are provided.

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 three sentences, front-loaded with the purpose, and packs behavioral nuance (UAT vs bot, pagination) without unnecessary filler. Every sentence contributes unique value, making it a model of concise, structured documentation.

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 tool has no output schema, so the description must compensate by explaining return values. It does partially: it notes the response carries viaUser and has hasMore/nextOffset for pagination. It does not list the document fields returned, but the key usage context is covered. Given the moderate complexity (3 params), this is sufficient, though not exhaustive.

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?

The input schema already documents all three parameters with 100% coverage. The description adds context about pagination by explaining how to use the returned nextOffset as the offset parameter, which reinforces the schema's 'Pagination offset from a previous nextOffset.' However, it does not add major new meaning for the query or page_size parameters beyond what the schema already states, so the baseline of 3 is appropriate.

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 opens with a specific verb and resource: 'Search Feishu documents by keyword.' This clearly states the tool's function and distinguishes it from sibling tools like search_contacts or search_wiki. The UAT/bot distinction further clarifies the exact scope of 'your documents,' making the purpose unambiguous.

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 on when the tool is appropriate by explaining the UAT-first behavior: 'with user identity (UAT) the search covers docs visible to YOU... via bot it only covers docs shared with the bot.' This helps an agent decide when to use it based on the authentication context. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of a 5.

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