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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses privacy and filtering behavior not visible in structured data: openNeeds only returns public/listed needs (已下架/已完成的不出), BP links are never delivered (only the hasBp boolean), and cloud users (user.isCloud=true) expose only user.cloud data with no contact info. It also prescribes the correct contact channel per user type, which no annotation could convey.

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 long but tightly structured: a front-loaded summary of returned sections, a labeled 【组合链】 workflow, and a numbered 【口径】 list of edge cases, so each sentence carries distinct information. The length is justified by the five behavioral nuances it must cover, but it is denser than a strictly minimal definition.

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?

With no output schema, the description carries the burden of documenting return shape, and it does so by enumerating the aggregate sections (canOffer, highlights, professions, works, openNeeds, appearances, roleProfile) plus the hasBp and user.cloud variants. It also covers the important edge cases (公开在架口径, cloud-user restrictions, existing-conversation alternative); only minor details such as ordering or pagination of works/openNeeds go unmentioned.

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% and the schema already documents id as '用户 id（cuid）', so the baseline of 3 applies. The description adds workflow context on where the id originates (search_people/list_needs_feed hits and the opcmenu://creator/{id} resource) but no additional format or constraint semantics beyond 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 a specific verb, resource, and scope: '按 id 一次拿全一个人的档案' and enumerates the exact aggregate sections returned (canOffer/highlights/professions, published works, openNeeds, appearances, roleProfile). It also differentiates from siblings by naming search_people/list_needs_feed as upstream entry points and get_conversation_needs as the alternative, so an agent can tell them apart without opening schemas.

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 【组合链】 section gives an explicit workflow: after a search_people/list_needs_feed hit, use get_creator to see the match, then proceed to contact_need or start_conversation. The 【口径】 section adds exclusions: use list_my_needs for one's own needs, prefer get_conversation_needs when a conversation already exists, and never start_conversation with cloud users (use send_cooperation_request instead). This is explicit when/when-not guidance with named alternatives.

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