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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints, so the bar is lower. The description adds substantial operational caveats: terms body is not returned by default and requires includeTermsBody=true; myMembership.id is a membershipId used to address update_my_organization_membership; PENDING application means do not re-apply because the server short-circuits; and applicant answer text is never agent-accessible. None of this contradicts the 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?

Dense but well-structured with three labeled sections: 【何时用】, 【组合链】, and 【口径/坑】. Each sentence carries actionable information that cannot be inferred from the schema or annotations. The when-to-use guidance is front-loaded, and the pitfalls are concise.

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 compensates by listing the full payload categories, the bodyLength pre-check, the membershipId addressing semantics, duplicate-application behavior, anonymous access, and the complete workflow chain. Nothing essential for correct invocation or follow-up decisions is missing.

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. The description elevates it by adding includeTermsBody semantics beyond the schema: '最长两万字，只在要念给用户确认时传' and '缺省 false'. It also explains the conditional use of the terms body via currentTerms.bodyLength. organizationId is generic but self-explanatory.

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 precise verb+resource: '一次拿全一个组织的身份／可见性／入会政策／协议摘要／申请要填哪几题／我的成员态／我现在能不能申请'. It enumerates the bundled data items and explicitly notes anonymous access for public organizations, making it distinct from application or membership-mutation siblings like apply_to_organization and update_my_organization_membership.

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?

Opens with 【何时用】 and gives an explicit trigger: when an activity is blocked (activity_members_only) or activity details show organization.canApply=true, call this tool with includeTermsBody=true, then apply_to_organization, then submit_signup. This is concrete routing guidance with a follow-up chain, clearly separating when to read an organization versus when to act on it.

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