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

Annotations only supply idempotentHint, so the description carries the behavioral load and does it well: it discloses that exposing plaintext phone numbers to OWNER/ADMIN is irreversible once seen ('关闭无法收回已所见'), that private orgs force showOnProfile=false, that results are returned per organization as updated/failed, and that on rate limiting only the failed ids should be retried. These are non-obvious operational facts an agent could not infer from the schema.

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?

Very dense but front-loaded with the auth/ownership constraint, then the changeable fields, then the read-first and scoping rules, then the risk warnings, then the verification/retry advice. Every clause carries information; the only cost is the slash-delimited shorthand style, which reads as terse rather than wasteful.

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 an eight-parameter mutation with no output schema, the description covers prerequisites, defaults, irreversible side effects, partial-failure reporting and retry strategy — enough for an agent to call it safely. The remaining gaps are the undefined contactSharing enum members and a slightly unclear minimum-selection constraint.

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 only 13%, so the description must compensate — and it largely does, mapping all eight switches to their meaning in prose and calling out organizationIds' omit-to-apply-to-all semantics. It still leaves the contactSharing enum values (MANAGERS, MEMBERS, HOST, CHAPTER, DEFAULT) undefined beyond NONE, and '至少一项' is ambiguous about a minimum-selection rule that the schema does not enforce (0 required parameters).

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?

It names the specific verb and resource (updating my own membership in organizations) and enumerates the concrete switches it controls: 主页展示, 组织撮合, 管理员联系方式, 服务或推广通知, hideFromDirectory, contactSharing. It also states what it is not — '不能改角色或踢人' — which separates it from set_organization_member_role and remove_organization_member in the sibling list.

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?

It gives an explicit prerequisite ('登录/仅本人'), a recommended read-first step ('先list_my_organization_memberships看现值'), a default-scope rule ('省略organizationIds批改全部组织'), and a hard precondition for sensitive changes (non-NONE contactSharing or contactVisibleToManagers=true requires explicitly naming each organization). When-to-use and when-not are both covered.

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