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

Goes well beyond the annotations: says cancel is irreversible and releases the room, that HotelRunner may notify the guest or the OTA channel, that a missing precondition yields state_change_is_not_available, and that the call consumes the property's 250/day and 5/min quota. The annotations (destructive, openWorld, non-idempotent) are consistent with and reinforced by this text.

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 'WRITE:' and the state machine, then consequences, then preconditions, then quota and endpoint — every clause carries load. It is a single dense block, though, and the quota/endpoint tail slightly dilutes scannability of the critical safety warning.

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?

No output schema exists, yet the description covers the success path, the specific failure code, quota cost, HTTP endpoint, and irreversibility. For a destructive two-event state transition, nothing an agent needs to decide or call safely is missing.

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 100%, so the baseline is 3, but the description adds the conditional requirement logic (cancel_reason is required only for cancel, confirm=true must be passed to gate a cancel) and enumerates the allowed reasons inline, which the schema only lists without context. The hr_number format itself is left to the schema, keeping it from a 5.

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 ('move ONE reservation to the next state') and enumerates the only two events, 'confirm' and 'cancel', with a one-line gloss of each. This clearly separates it from read siblings like hotelrunner_get_reservation and from the unrelated hotelrunner_update_room_calendar.

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 explicit preconditions (requires_response must be true and the event must be in next_states, checkable via hotelrunner_get_reservation) and an explicit when-not ('only cancel when the user clearly asked for it'). It also names the alternative tool for the precondition check, which is exactly the routing an agent needs.

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