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

Annotations already cover safety (readOnly, non-destructive), but the description adds context they cannot: the required 'bookings' scope, the constraint that only the caller's own paid bookings qualify, the closed enumeration of possible states, and a mandatory user-facing disclosure step. This is materially more than the annotations provide.

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 purpose, then returns, then workflow rules, then auth, with no filler sentences. It is a dense single block that would read faster split into short lines for return fields and constraints, but nothing is redundant.

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?

There is no output schema, and the description compensates by naming the return fields (state, canCancel, cancellationType, deadlineUtc, message, onCancel) and enumerating the state values. For a read-only pre-flight check, nothing needed to invoke it correctly 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 'pnr' is already documented, but the description adds scoping meaning the schema does not: the booking must be the caller's own and paid. It does not add format hints, which is fine given a fully covered single string parameter.

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: checks whether one of the caller's own paid Stay bookings can still be cancelled, and what the member would get back. It also distinguishes itself from the nearest sibling by framing itself as the pre-check that must run before cancelBooking.

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?

Explicit sequencing ('Always call this first... before offering cancelBooking') and an explicit prohibition with its trigger condition ('When state is expired... do not offer cancelBooking'). The agent knows both when to call this and when to withhold the follow-up tool.

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