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

Annotations already flag destructive and open-world, but the description adds real value beyond them: the advisor gets notified and confirmed reservations are handled under the hotel's cancellation policy rather than simply voided. It doesn't say what happens to the session record afterward or how failures surface.

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 critical warning 'SENSITIVE WRITE' is front-loaded, and all three sentences carry distinct information: severity, scope of the pre-confirmation case, and the confirmed-reservation fallback. No filler.

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 one-parameter destructive mutation with no output schema, the description covers consequences and the advisor side effect reasonably well. The key gap is parameter meaning and any indication of what state the booking session is left in, which an agent needs before calling a destructive tool.

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 0% and the single required parameter session_id is never explained — the description doesn't say it is a booking-session ID or where to obtain it (e.g., from get_booking_session or create_booking_session). With no annotation or schema help here, the description should compensate and does not.

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 (withdraws a booking) plus a temporal scope condition (before the hotel confirms it) that separates it from the sibling cancel_booking for confirmed reservations. It never names cancel_booking explicitly, so the differentiation must be inferred.

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 'before the hotel confirms it' clause implies when to use it, and the second sentence sketches the alternative path for confirmed reservations. But it doesn't name the alternative tool or state an exclusion directly, leaving the agent to map 'confirmed reservations ... through the advisor' to cancel_booking.

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