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

Annotations already cover the safety profile (readOnlyHint true, destructiveHint false), and the description reinforces it with 'The call changes nothing'. It adds genuinely new context the annotations lack: the auth requirement (user's Cotlet API key with access to this app) and the shape of the response.

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 return semantics before the airline rules and auth note. Each sentence carries distinct information, though the conversational opening ('What you get back if you cancel this trip now, under its ticket type') is mildly wordy.

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 no output schema, the description usefully enumerates the returned fields and the ticket-type constraints, and it names the required credential. Complete enough for a single-parameter read tool, with only minor gaps around the full refund-option structure.

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?

Only one parameter, fully documented at 100% coverage by the schema ('Booking number from list_trips'). The description adds no syntax or sourcing detail beyond that, so the baseline of 3 applies.

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+resource (get cancellation/refund options for a trip) and describes the payload (refund_option_id, destination of funds, amount). The line 'The call changes nothing' functionally distinguishes it from the sibling kiwi-com_cancel_trip, which actually cancels.

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 framing 'what you get back if you cancel this trip now' makes the preview-before-cancelling use case clear, and the per-ticket-type rules (Saver/Standard cancel single flights, Flexi only whole booking) tell the agent when options are even available. It does not, however, explicitly name cancel_trip as the alternative action.

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