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

The description adds authentication context ('需要登录') and pagination/idempotency guidance ('勿反复从首页刷'), which go beyond the annotations. But annotations declare readOnlyHint=false and idempotentHint=false, and the description does not explain what side effects or state changes these hints imply. The read-oriented wording ('读') leaves the non-read-only behavior unexplained rather than contradicted.

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 short, dense, and front-loads the most important constraint ('需要登录'). Every clause carries information, though the telegraphic bracketed style and jargon like 'not_your_need' make it slightly harder to parse than an ideal two-sentence structure.

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 covers authentication, workflow, and pagination strategy, which is substantial given the detailed input schema. However, with no output schema, it only minimally explains the return content ('匹配分/理由和作者需求') and does not clarify the non-read-only side effects, leaving gaps for a recommendation tool.

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 the baseline is 3. The description still adds practical semantics beyond the schema by stating that cursor should carry already-seen IDs and that the agent should not restart from the first page, clarifying how 'cursor' and 'seen' interact during pagination.

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 states a specific verb and resource: it lets the agent 'read match score/reason and author need' for a need, which maps to the tool name get_need_recommendations. It also constrains scope to 'only my own needs' and warns against retrying 'not_your_need'. However, it does not explicitly distinguish this from similar siblings such as get_my_need_matches, leaving some ambiguity.

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 gives an explicit workflow chain: list_my_needs → recommendations → get_creator → start_conversation/contact_need. It states a clear exclusion ('not_your_need勿重试') and a pagination rule ('cursor携已看ID，勿反复从首页刷'). This is strong when-to-use and when-not-to-use guidance.

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