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

Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds substantial behavioral context beyond that: logged-in vs anonymous sorting differences, matchScore/matchReason inclusion, card aggregation by author, max 6 authorNeeds, pagination semantics ('cursor 原样回传延续同一副牌；不传 = 重新洗牌'), and the business rule that contact is unlimited with no fee/reward. No contradiction with annotations.

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-organized with labeled sections (【何时用】【结构】【组合链】【口径】【分页】) that front-load the most important usage decision. Every section earns its place by providing operationally relevant guidance rather than filler. Despite its length, it remains scannable and purposeful.

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 there is no output schema, the description compensates by explaining the card layout, authorNeeds limit, ordering behavior, match fields, pagination, and related workflow. It also covers the business context (no quota, no reward, direct chat) that an agent needs to set expectations. This is complete for a list-feed tool with only three optional parameters.

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 schema already explains type, limit, and cursor. The description adds valuable behavior beyond the schema, especially for cursor: passing it back continues the same paginated set, while omitting it reshuffles the deck. This extra pagination semantics justifies a score above the baseline 3, though most parameter meaning still comes from 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 opens with an explicit when-to-use statement: it is the main entry for the demand-exchange feed, showing '大家都在找什么' and needs an agent can help with. It also distinguishes itself from targeted tools by naming search_needs / search_people as the directed-search alternative. The card structure (one person per card, author.canOffer + authorNeeds) makes the resource and shape unmistakable.

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 【何时用】 section states exactly when this tool is appropriate, while the 【组合链】 section gives the follow-up workflow: contact_need → send_message. It explicitly routes targeted discovery to search_needs / search_people and recommends update_my_profile to improve ranking. Exclusions and alternatives are explicit, not merely implied.

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