list_needs_feed按作者聚合在架需求，每人最多6条，primary优先；登录按本人canOffer轻排序。cursor续同批，缺省重排；无名额或报酬承诺。【组合链】need.id→get_need→contact_need→send_message；定向查search_needs，自述不足update_my_profile(canOffer)。
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | 按需求类型过滤：EXPERIENCE（寻找产品/作品） | QA（答疑求助） | RESOURCE（介绍资源） | COLLAB（寻求合作） | FINANCING（融资需求） | CHAT（找人聊聊找灵感） | GIG（兼职招募） | OTHER（其它）；不传则全部 | |
| limit | No | 返回条数，默认 20 | |
| cursor | No | 分页游标 nextCursor，原样回传 |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real behavioral context beyond the annotations: per-author cap of 6, primary-priority ordering, login-dependent canOffer sorting, cursor continuing the same batch vs. default reshuffle, and a content disclaimer that no quota or payment is committed. With annotations already covering safety flags, this is strong added value. It does not address why readOnlyHint=false / idempotentHint=false for a listing operation, leaving the mutation profile ambiguous.
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?
Dense but front-loaded: aggregation/sort rules first, cursor semantics next, then the tool chain. Every sentence carries information, though the bracketed chain block and terse jargon hurt immediate parseability.
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?
No output schema exists, yet the description covers aggregation, ordering, pagination behavior, and the follow-up chain, which is most of what an agent needs. It stops short of describing the returned fields or the shape of a feed item.
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 coverage is 100%, so the baseline is 3, but the description adds cursor semantics the schema lacks ('cursor续同批，缺省重排') — telling the agent that omitting the cursor reshuffles rather than continuing. The type filter and limit are left to the schema, which is acceptable given full coverage.
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?
States a specific verb+resource (aggregates on-shelf needs by author) with concrete scoping rules (max 6 per author, primary first, canOffer-based light sort). An agent can tell it apart from search_needs, which the description names explicitly. Docked one point because key qualifiers ('primary', 'canOffer', '在架') are jargon left undefined.
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?
Gives an explicit routing rule: for targeted lookups use search_needs, and if the user's self-description is insufficient, use update_my_profile(canOffer). It also supplies the downstream chain (need.id→get_need→contact_need→send_message), so the agent knows how to act on results rather than just fetch them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.