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

The description adds key behavioral details beyond the annotations: the row is deactivated not deleted, and historical events stay available via recent_alerts. It also discloses ownership enforcement, which is an important access-control behavior. This goes beyond the basic readOnly/destructive hints.

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 two sentences long, front-loaded with the main action. Each sentence contains distinct value: cancellation, ownership, and deactivation behavior. There is no redundant or filler content.

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?

The description explains the outcome (deactivated), the ownership restriction, and the impact on historical data. It does not specify the return value or error handling, but for a simple cancellation tool with a single parameter, this is a minor omission.

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?

The input schema describes the lone 'id' parameter as 'Subscription id (uuid) returned by subscribe,' providing full coverage. The description only repeats 'by id' without adding extra meaning, so it does not outperform the schema baseline.

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 begins with 'Cancel a subscription by id,' a specific verb and resource. It distinguishes itself from siblings like subscribe and list_subscriptions by focusing on the cancellation action, and further clarifies the semantics with ownership and soft-deletion details.

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 gives clear context on when to use this tool: to cancel a subscription while preserving historical events. It does not explicitly name alternatives, but the context implies using this when you want to stop alerts without deleting history, and it notes an important constraint (only your own subscriptions).

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