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

Annotations declare destructiveHint=true and the description confirms this with the explicit **不可逆** (irreversible) warning and the concrete consequence: the invite vanishes from the other party's pending list. It also discloses the auth requirement (only the goal initiator can withdraw), the error condition (not in pending state), and advises against futile retries — substantial behavioral context well beyond what the annotations alone provide.

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 organized into labeled sections (login, when-to-use, combination chain, pitfalls) and front-loads the most critical facts. Every sentence earns its place — the chain, the auth restriction, the irreversibility warning with user-confirmation instruction, and the no-retry error guidance are all essential and none are redundant.

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 single-parameter tool with no output schema, the description covers everything needed to call it correctly: prerequisite (login + being initiator), parameter acquisition via the chained tool, irreversibility, error conditions, and the correct recovery action. Nothing an agent needs in order to execute or safely reason about this mutation 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 0%, so the description must compensate for the single undocumented parameter. The combination chain explains exactly how to obtain inviteId — get_collaboration_goal(goalId, include:["invites"]) — and discloses that it is only visible to the goal initiator. This adds real meaning beyond the schema's bare maxLength/minLength constraints, though it stops short of describing the ID's format.

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 states a specific verb (撤回/withdraw) + resource (collaboration invite) with a precise scope: only invites this goal sent out that haven't been responded to yet. This clearly distinguishes it from siblings like respond_collaboration_invite (responding to an invite received) and invite_collaboration_member (creating an invite), so an agent can select it correctly without opening any schema.

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?

An explicit 【何时用】(when to use) section sets the trigger condition and even notes the App lacks this entry point, which justifies the tool's existence. Pitfall ③ adds a when-NOT-to-use rule (already accepted/declined/expired) plus the corrective action (check if they've joined). It doesn't name a specific sibling to prefer instead, but the boundary is clear enough that an explicit alternative isn't necessary.

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