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

Annotations declare the safety profile (destructive=true, idempotent=true), but the description adds material context they cannot carry: the refund follows the rate terms, is credited back to the card through Nuitee, and the free-cancellation window is bounded by a deadline. It also discloses the auth blocker (no Quub API key on this connection), which is exactly the kind of precondition an agent needs before invoking a destructive tool.

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?

Front-loaded with the purpose and refund consequence, then constraints, then prerequisites. Five short sentences with little waste, though 'Needs the guest email' is mildly redundant against a required schema field and could be dropped.

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 destructive, irreversible cancellation with no output schema, the description covers everything an agent needs: what is refunded, where the money goes, which rates are eligible, who must request it, and that the call is currently blocked pending an API key. Nothing material 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 coverage is 100% and both parameters are required, so the schema already documents booking_id and guest_email. The description only restates that the guest email is needed, adding no format, provenance, or edge-case detail beyond what is structured. 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?

States a specific verb and resource ('Cancels a confirmed booking') and narrows the scope with two qualifiers: the rate must be refundable and the booking must have been made with this key. No sibling tool performs cancellation, so the agent can immediately place it in the toolset.

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?

Gives an explicit gate ('Only call this when the guest asked for it'), an explicit exclusion ('Non-refundable rates cannot be cancelled online'), and routes to the correct alternative tool for the blocking prerequisite ('this connection has none yet: use request_api_key'). When-to-use, when-not-to, and the prerequisite path are all named.

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