cancel_booking

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

With no annotations present, the description carries the full disclosure burden and does so excellently. It reveals that cancellation is immediate, irreversible (the server cannot undo it), notifies the venue exactly as a manage-link cancellation would, is safe to retry (idempotent — cancelling an already-cancelled booking returns the same result rather than an error), and returns an error for bookings whose start time has passed. This is precisely the behavioral context an agent needs for a destructive operation.

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 longer than average, but every sentence earns its place: purpose, identification, guest-confirmation requirement, irreversibility, retry safety, error condition, and rescheduling workflow. Information is front-loaded (purpose first) and densely packed without redundancy. For a destructive tool with no annotations, this length is justified, not bloated.

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 2-parameter tool with no annotations and no output schema, the description is remarkably complete: it covers the action, parameter derivation, failure modes, retry semantics, irreversibility, and the rescheduling path. The only gap is that it never describes the return value or success response format, which is somewhat expected given the absence of an output schema. An agent has everything necessary to invoke it 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 description coverage is 100%; both booking_id and manage_token are already documented in the schema, including their provenance from create_booking or the guest's manage link. The description adds only the framing that the pair identifies the booking 'like check_booking,' which marginally reinforces that both are required together but adds little beyond the schema. 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?

The description opens with a specific verb and resource: 'Cancel an upcoming booking and release its slot to other guests.' This states not just the action but its consequence, making it immediately distinguishable from siblings like check_booking, create_booking, and check_availability. No ambiguity about what operation is performed.

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 guidance ('Confirm with the guest before calling'), an explicit when-not condition (bookings whose start time has passed cannot be cancelled), and an explicit alternative for a related scenario ('To move a booking to another time, cancel it and create a new one'). It also signals the retry posture. It slightly misses an explicit statement of when to prefer sibling tools like check_booking first, but the key routing is covered.

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