hemmabo_booking_cancel

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

Annotations already mark the tool as destructive and idempotent, but the description adds critical specifics: 'a repeat cancel is refused as already cancelled and never triggers a second refund,' 'Rate-limited per token,' and the distinction that a Bearer token alone is insufficient without a matching guestToken. It also clarifies that it only applies to confirmed bookings and that the reason is shown to the host, with a default message. This goes well beyond the annotation hints and gives the agent a clear behavioral model.

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?

The description is dense but every sentence earns its place. It is front-loaded with the core purpose, then moves to usage boundaries, then behavioral cautions, then parameter-specific clarifications. There is no repetition or filler. The length is proportionate to the tool's complexity (three parameters, destructive effect, auth nuances). Structurally clear and efficient.

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, idempotent tool with an output schema (which covers return values), the description covers all necessary operational context: when to use, when not to use, alternatives, security requirements, parameter constraints, and side effects. The presence of an output schema means the description need not describe the return payload, so no essential information is missing. An agent can confidently call this tool correctly based on the description alone.

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?

Although the schema covers 100% of parameters, the description significantly enriches understanding. It explains that guestToken is a per-booking secret returned at creation/checkout, that it grants no authority over other bookings, and that a valid Bearer token is not sufficient. It clarifies reservationId must be a booking UUID, never a propertyId, and must be paired with the matching guestToken. The reason parameter's optionality and default text are also described. These details are essential for correct invocation and go far beyond the schema's field descriptions.

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 and resource: 'Cancel a confirmed booking and process the Stripe refund per host cancellation policy.' It clearly states what action is performed and on what object, and distinguishes it from the reschedule sibling by naming the alternative explicitly. The purpose is unambiguous and cannot be confused with any of the other tools.

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 description provides explicit when-to-use and when-not-to-use guidance: 'Use when the guest explicitly requests cancellation — if the guest wants new dates instead of ending the stay, use hemmabo_booking_reschedule instead. Do not use for pending/unpaid bookings — those expire automatically.' It also directs the caller to preview the policy via hemmabo_booking_status. This is textbook usage guidance with named alternatives and excluded scenarios.

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