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

Annotations declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds critical nuance: ownership enforcement ('only cancel your own subscriptions') and the non-destructive deactivation behavior ('deactivated, not deleted'). This explains the side effects beyond what annotations alone convey and aligns with them, with no contradiction.

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, perfectly front-loaded with the action first, then constraints and side effects. Every sentence earns its place with no redundancy or 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 single-parameter tool with no output schema, the description covers purpose, ownership, side effect, and points to recent_alerts for historical data. It is complete for the tool's complexity, and the absence of return value details is acceptable given the simple context.

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% with a clear parameter description ('Subscription id (uuid) returned by subscribe'). The description adds an ownership constraint on the id, reinforcing that the id must belong to the caller. This goes slightly beyond the schema, providing additional semantic meaning.

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 opens with 'Cancel a subscription by id', providing a specific verb (cancel) and resource (subscription), and immediately clarifies the input mechanism. This distinguishes it from sibling tools like subscribe (creation) and list_subscriptions (listing), making the purpose unmistakable.

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?

It gives clear usage context: ownership is enforced and cancellation is by id, implying you should only use this for your own subscriptions. It also indicates the alternative for historical events (recent_alerts), though it doesn't explicitly state when NOT to use this tool versus alternatives. This is strong guidance but not fully explicit.

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