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

Annotations already declare destructive=true, idempotent=false and readOnly=false, but the description adds far more: cancellation cannot be undone online, refund/credit lands in the wallet automatically, Custom policy ('request') only emails a request and leaves the booking active, and all three parties are emailed. It also names the required 'bookings' scope, which no annotation conveys.

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 the action, then preconditions, then consequences, then the policy exception, then scope — a logical reading order with no filler. It is dense at five sentences, but nearly every clause carries behaviorally load-bearing information.

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 three-parameter mutation with no output schema, the description covers preconditions, irreversibility, financial outcome, the divergent 'request' path, notification side effects, and authorization scope. Nothing an agent needs to call it 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 description coverage is 100%, so pnr, reason and confirm are already documented, and the description largely restates confirm: true. It adds marginal context by framing confirm as a consent gate tied to the member's explicit statement, but adds nothing about reason or pnr beyond the schema.

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 precise verb and resource scoped to "one of the caller's own paid Stay bookings under the Stay's cancellation policy", which is unmistakably distinct from the read-only getCancellationOptions and listMyBookings siblings. An agent knows exactly what object is affected and under what governing rules.

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 gating sequence: only call after getCancellationOptions returned canCancel: true, after relaying message and onCancel text to the member, and after the member explicitly agreed, with confirm: true required. The alternative/read tool is named and the precondition that routes to it is stated.

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