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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds value beyond them: it flags irreversibility, discloses the side effect of initiating a refund, and describes token validation failure modes. For a mutation tool, that is rich 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?

Three tight sentences, front-loaded with purpose and reversibility, then prerequisites, then the sibling pointer. No sentence is redundant.

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?

With an output schema present, return values need no explanation; the description covers workflow position, irreversibility, token requirements, and refund implications. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so all three parameters are already documented (including the token's origin and the confirmation code format) and the description adds no syntax or format detail beyond that. This is the baseline case where the schema carries the 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 opens with a specific verb+resource ('Second of two steps to cancel a booking: cancels it and starts any refund due'), placing it precisely in the two-step workflow and distinguishing it from request_cancel_token, which is named as step 1. An agent can tell it apart from siblings without opening the schema.

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 states the exact prerequisites (confirmation code plus the single-use token request_cancel_token emailed to the guest) and the negative condition ('a missing, expired or already-used token is rejected'). It also routes to get_cancellation_policy for refund terms, giving explicit when-to-use and companion-tool guidance.

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