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

Annotations only give readOnly=false, openWorld=true, destructive=false. The description adds real behavioral context beyond that: cancellations are handled under airline fare rules, confirmation is on by default and can be toggled off per tool, the action reaches other people so the user must be consulted each call, and it requires a Cotlet API key scoped to this app. That is materially more than the annotations convey.

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 and information-dense, with the verb and refund linkage first. Slightly repetitive on the confirmation requirement ('By default you confirm each call' vs 'confirm with the user before each call'), though the second instance adds the 'reaches other people' rationale, so the redundancy is minor.

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 mutation tool with no output schema and an external side effect, the definition covers the essentials: what gets cancelled under each ticket type, how to source the refund option, the confirmation/auth requirements, and cross-account impact. An agent has everything needed to call it correctly and safely.

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 already 100%, so baseline is 3. The description earns more by explaining the relationship between refund_option_id and get_cancellation_options, and by clarifying the conditional semantics of flight_ids (only valid for Saver/Standard; omitted means whole trip). This adds meaning the schema descriptions alone do not fully capture.

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 (cancel) plus resource (trip) and immediately ties the action to a refund chosen from get_cancellation_options. This clearly separates it from sibling kiwi-com_get_cancellation_options (which only lists options) and kiwi-com_get_trip/list_trips, so an agent can pick it 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?

Gives strong invocation context: pass refund_option_id from get_cancellation_options, and note that Saver/Standard tickets allow single-flight cancellation via flight_ids while Flexi cancels the whole booking. It stops short of explicitly naming when NOT to use it, but the prerequisites effectively define the triggering condition.

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