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

Annotations already declare idempotency and non-destructiveness; the description adds valuable context beyond that: paired-message visibility, the separate 'leave the room' action, and the money-boundary ('or spend money'). This enriches an agent's mental model of the side effects without contradicting 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?

Three tight sentences with no filler: purpose, retry safety, then boundary caveats. Each sentence contributes information an agent needs before invoking the tool.

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 simple idempotent cancel operation, it covers the necessary boundaries and alternative behaviors well. The only gap is outcome/return semantics (e.g., whether success is confirmed), and there is no output schema to fill that gap.

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?

With only 50% schema description coverage (intro_id has no schema description), the description compensates by saying the request is identified 'by its ID', together with the pattern expressing the exact format. agent_key is already well documented in the parameter's own description, so the description does not need to repeat it.

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?

Opens with a specific verb and resource: 'Withdraw your own undelivered collaboration request by its ID.' It also differentiates from siblings inline with 'Does not cancel another request' and points out a semantically adjacent action ('pass to leave the room'), so an agent can distinguish it from invitation, join, and room-management tools.

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?

States the applicable condition (your own, undelivered request) and explicitly rules out a common confusion ('Does not cancel another request'), plus notes retrying is safe. It does not name alternative sibling tools explicitly, so the when-not-to-use guidance is implied rather than enumerated.

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