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

Beyond annotations (idempotentHint true, destructiveHint false), the description adds critical behavioral context: ownership enforcement, deactivation rather than deletion, and availability of historical events via 'recent_alerts'. This fully informs the agent of side effects and data persistence.

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 three sentences, directly addressing purpose, constraint, and consequence. Every sentence adds value with no redundancy or fluff.

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?

Given the simple input (single parameter) and presence of annotations, the description sufficiently covers purpose, ownership constraint, mutation behavior, and post-action data availability. No output schema needed as the tool is a void mutation.

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 covers 100% of parameters with a clear description of 'id' as a UUID returned by subscribe. The tool description adds no further parameter semantics beyond reiterating ownership enforcement, which is behavioral rather than parameter-specific. Baseline score for high coverage.

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 clearly states 'Cancel a subscription by id,' specifying the verb (cancel) and resource (subscription). It further clarifies ownership enforcement and the deactivation vs deletion behavior, distinguishing it from siblings like 'subscribe' and 'list_subscriptions'.

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?

The description implicitly guides usage by noting ownership enforcement ('you can only cancel your own subscriptions') and explaining that historical events remain accessible via 'recent_alerts'. It does not explicitly name alternative tools or conditions for non-use, but the context is clear.

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