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

Annotations already indicate idempotent( true ) and not destructive( false ). The description adds beyond annotations by clarifying ownership enforcement, that cancellation is a deactivation rather than deletion, and that historical events remain available via 'recent_alerts'. This provides meaningful behavioral context.

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?

Two sentences with all essential information front-loaded. No superfluous words; every sentence adds value: first states core action, second adds constraints and side effects.

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 tool's simplicity (one parameter, no output schema), the description fully covers purpose, constraints, side effects, and even references a related sibling tool ('recent_alerts') for follow-up actions.

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 100%, and the description does not add any extra meaning beyond what the schema's property description ('Subscription id (uuid) returned by subscribe.') already provides. The description mentions 'by id' but that is already implied.

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?

Description clearly states 'Cancel a subscription by id.' It uses a specific verb ('cancel') and resource ('subscription'), and distinguishes itself from siblings like 'subscribe' and 'list_subscriptions' by focusing on cancellation and soft-deletion behavior.

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?

Explicitly states ownership enforcement ('only cancel your own subscriptions') and explains that the row is deactivated, not deleted, with history still accessible via 'recent_alerts'. This provides clear context on when to use and what happens after, though it doesn't mention explicit alternatives for other users' subscriptions.

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