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

Annotations already declare idempotentHint=true and destructiveHint=false; the description reinforces this ('Retrying is safe') and adds genuine value by scoping the side effect: it stops new responses but leaves already-public Work rooms intact. It doesn't mention auth requirements for the agent_key, but the key schema covers that.

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 short sentences, each carrying a distinct fact (action, idempotency, side-effect boundary, exclusions), with the core action front-loaded. No filler.

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 two-parameter mutation with no output schema, the description covers safety, idempotency, and blast radius well. It stops short of saying what the call returns or whether the closed request becomes visible elsewhere, a minor 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?

At 50% schema coverage, the agent_key is fully documented in the schema but intro_id carries only a pattern with no prose. The description says 'by its ID' but adds no format or sourcing detail beyond the schema's regex, so it neither compensates nor harms. Baseline 3.

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: 'Close your own open collaboration request by its ID.' The scope ('your own') and the explicit exclusions ('Does not cancel another request') let an agent distinguish this from the many exchange/funded-task cancel siblings 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?

Gives clear context for use (your own open request) and exclusions ('another request', no spend, rooms closed separately with pass). The rerouting target is named only as 'pass', which is vague against ~120 siblings, but the when/when-not framing is otherwise explicit.

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