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

Adds substantial context beyond the annotations: whole-order-only semantics, the conditional free-cancellation window, confirmation behavior ('By default you confirm each call'), that the action 'reaches other people' and therefore needs user confirmation, and the auth requirement ('Cotlet API key with access to this app'). It does not explicitly state irreversibility or the cost consequence of cancelling a non-refundable booking, which would fully close the loop on a cancellation mutation.

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-loads the purpose and scope, then layers eligibility, prerequisite, confirmation, and auth constraints in short sentences that each carry information. The confirmation-toggle sentence is slightly UI-flavored but still informs calling behavior, so little is wasted.

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 single-parameter mutation with annotations and no output schema, the description covers what an agent needs: when it may be called, what it affects, required prerequisites, side effects on other people, and credential needs. Nothing material is missing before invoking it.

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, and the schema already documents it fully ('Order ID from list_bookings'), so the description adds no syntax or format detail on top of the schema. Baseline 3 is correct when coverage is 100% and the parameter is self-explanatory.

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 ('Cancel a whole booking', 'Cancels one whole order') and immediately bounds the scope by ruling out partial cancellation. It also names a related sibling ('Check get_booking first'), so an agent can place it among the other tiqets_* booking tools without opening a 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 an explicit prerequisite ('Check get_booking first') and the eligibility/refund window ('Free cancellation applies only if you chose it at booking, and runs until 23:59 on the day before the visit'). It does not explicitly contrast with alternative actions such as tiqets_reschedule_booking, so the 'when-not' case is left to inference.

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