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

Annotations already declare destructiveHint=true and idempotentHint=true. The description adds valuable behavioral context: it refunds in full, releases the slot, reverses payment, and requires the email used at order creation. It also explains what to do if the tool fails. This enriches the annotation-provided safety profile 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?

The description is front-loaded with the deprecation status, which is critical. Each sentence provides necessary information: deprecation, alternative, behavior, prerequisite, confirmation requirement, and fallback. It is somewhat wordy but every part earns its place. A slight condensation could make it more concise, so it does not earn a 5.

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 simple two-parameter cancellation tool with annotations present but no output schema, the description covers all essential aspects: purpose, deprecation, refund behavior, prerequisite, confirmation protocol, and error fallback. It gives an agent enough context to invoke the tool appropriately and handle failures.

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 email parameter with 'Must match the order's email', and the description rephrases this as 'Requires the email the order was created with', adding little new meaning. The order_id parameter has no schema description and the description only implies it via 'order number' in the fallback hint. Schema coverage is only 50%, and the description does not fully compensate for the missing order_id semantics.

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 the tool's action: 'Cancel a booking and refund it in full.' It also distinguishes itself from the sibling tool cancel_order by explaining that cancel_order is the preferred, up-to-date name and is accurate for certificates as well as appointments. This makes the purpose unambiguous.

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 explicitly says to prefer cancel_order instead of this deprecated alias, giving a clear alternative. It also instructs to 'Confirm with the buyer before calling' and explains the consequences (releasing slot, reversing payment), providing concrete usage guidance and when-not-to-use scenarios. The fallback instruction for failure is also present.

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