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

Annotations only supply idempotentHint, so the description carries the real behavioral load and does it well: login required, the leave is effectively irreversible (re-apply or be re-invited), a pending application is withdrawn as a side effect, and a user confirmation is demanded before firing. It does not describe the response shape or any resulting state on the org's member lists, which is the remaining gap for a mutation.

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?

Front-loaded with the login requirement and the core action, then consequences, then the call sequence, then exclusions. Every sentence carries information (irreversibility, confirmation, owner restriction, alternative tool), though the block is dense and would read faster as separated clauses rather than one run-on paragraph.

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 one-parameter mutation with only idempotentHint and no output schema, the description supplies everything an agent needs: prerequisites (login, ownership status), the id-sourcing step, the human confirmation gate, irreversible consequences, and the sibling that covers the lookalike use case.

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% and the single organizationId is already documented as '组织 id', so the baseline would be 3. The description adds genuine meaning by telling the agent where to source that id from (list_my_organization_memberships) and that the user must confirm it before the call.

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 (退出一个组织 / leave an organization) and adds the non-obvious side effect of withdrawing the caller's pending application to that org. It also implicitly separates itself from update_my_organization_membership and list_my_organization_memberships, so an agent can route correctly 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?

Gives an explicit call sequence (list_my_organization_memberships to get the org id → user confirmation → this tool) and explicitly names the alternative for the adjacent-but-different need (update_my_organization_membership to just mute promotions). It also states when the tool is unavailable: owners must transfer first, and orgs under an acting 主理人 cannot be left.

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