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

The description goes well beyond the annotations. It reveals that the operation is a deactivation (not deletion) and that historical events remain available via 'recent_alerts', which is critical behavioral context. The annotations already indicate non-destructive and idempotent, and the description aligns without 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, no fluff. The verb and resource are front-loaded, and every sentence adds essential information (ownership, deactivation vs deletion, historical data).

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 covers the core purpose, behavioral effect, ownership, and reference to historical availability. For a simple unsubscription tool with one parameter, it is mostly complete. Minor gap: it does not mention error handling (e.g., invalid id or not owned) or prerequisites like authentication.

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 parameter 'id' is well-described in the schema as 'Subscription id (uuid) returned by subscribe.' The description mentions 'by id' but adds no additional constraint or formatting beyond the schema. Baseline 3 is appropriate.

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 uses the strong verb 'Cancel' and specifies the resource 'subscription by id', clearly distinguishing it from sibling tools like 'subscribe' and 'list_subscriptions'. It also clarifies the effect (deactivation vs deletion) and ownership enforcement.

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 states ownership enforcement, implying the user must own the subscription to cancel. It references 'recent_alerts' for historical data, providing context. However, it does not explicitly state when not to use the tool or compare to alternatives like 'subscribe' (for creating) or other cancellation methods.

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