Cancel hotel booking

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real value beyond them: it discloses the financial consequence (a non-refundable booking or one past its free-cancellation deadline can be charged in full) and the auth rule (server only acts when bookingId and email match). It stops short of describing the post-cancellation response/confirmation state, which keeps it from a 5.

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?

Two sentences, no wasted words, with the prep step and consequence front-loaded before the credential requirement. The second sentence mildly repeats the schema's auth rule, which is the only redundancy.

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 mutation with no output schema, the description covers the prerequisite lookup, the customer-confirmation requirement, the penalty risk, and the credential matching rule. The main omission is any statement of what a successful cancellation returns or how failures surface, but that is minor given the richness elsewhere.

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 the schema already documents bookingId, email, and the optional lastName including the matching check. The description restates the bookingId/email requirement but adds no new syntax, format, or fallback guidance, so baseline 3 applies.

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+resource ('Cancel a confirmed hotel booking') and implicitly distinguishes itself from the sibling cancelExperienceBooking, which cancels a different resource type. An agent can select this over the other cancel tool without opening the schema.

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 prerequisite workflow ('First check the cancellation policy with `get_bookings_bookingid` and confirm with the customer') and names the sibling tool to use beforehand. It also states the condition under which cancellation carries a penalty, which is the key decision context for invoking this tool.

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