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

Annotations are minimal (readOnlyHint=false, openWorldHint=true, destructiveHint=false), and the description carries real extra weight: it cancels the booking, emails the guest, the comment routes to Hostelworld support not the guest, per-call confirmation is on by default and toggleable, it reaches other people so the user must be confirmed, and a Cotlet API key scoped to this app is required. The only lingering gap is a mild tension between cancelling a confirmed booking and destructiveHint=false; the description does not squarely address reversibility.

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 and readable, but it re-states the core action twice ('Cancel a booking as a no-show and email the guest' then 'Marks the booking as a no-show, which cancels it and emails the guest') and repeats the Pay Now exclusion. Roughly a third of the text is redundant restatement rather than new constraint.

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?

With no output schema, the description still covers everything needed to invoke safely: timing eligibility, rate-type and group exclusions, where the comment goes, confirmation behavior, external-side-effect warning, and auth requirements. An agent has no unanswered question before calling.

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. The description adds genuine meaning beyond the schema by clarifying that the comment is a note to Hostelworld support and never shown to the guest, which is exactly what determines whether an agent should put guest-facing text there.

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 plus consequences: 'Cancel a booking as a no-show and email the guest.' It distinguishes itself from siblings like hostelworld_acknowledge_booking and hostelworld_get_booking by naming the exact action and outcome, so an agent can tell it apart without opening any 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?

Explicit when-to-use and when-NOT-to-use rules: available from the check-in date, not for Pay Now rates, not for a group where only one guest is missing, and precise windows (until 23:59 for one-night, 48 hours after check-in for longer stays). Nothing is left to inference.

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