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

Annotations only declare readOnlyHint, so the description carries the rest: a hard 200-member ceiling with nextCursor paging, and the notable privacy behavior that phone numbers are omitted entirely rather than masked. These are real traits an agent cannot get from the schema. It stops short of saying what happens when the roster exceeds 200 or whether pending invitees appear.

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?

Semicolon-delimited fragments, front-loaded with the authorization gate before paging and id semantics. Dense but every clause carries information; the only cost is the telegraphic style, which slightly slows parsing.

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?

For a read-only, four-parameter list tool with full schema coverage and no output schema, the description covers access control, pagination limits, privacy of returned fields, and downstream id usage. Remaining gaps (default sort, inclusion of inactive or invited members) are secondary but would matter for a roster 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 q/limit/cursor/organizationId meanings are already documented, and the description adds no syntax or format detail beyond them. Its id guidance concerns returned fields (user.id vs membershipId) rather than the input parameters, keeping this at baseline.

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 and resource ("列组织成员") with the access condition (login/OWNER/ADMIN) attached, so the agent knows exactly what it returns. It does not name the near-siblings (list_alliance_organization_members, list_my_organization_memberships), so the boundary still needs inferring from the org-scoped permission gate.

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 concrete preconditions (must be logged in and OWNER/ADMIN) and post-call routing: user.id goes to get_creator/start_conversation, while membershipId is the handle for member operations and must not be swapped with userId. That is actionable guidance, though it never states when to prefer a different member-listing tool.

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