prepare_booking_cancellation

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds value by detailing behavior: it matches the schedule reservation internally, accepts no reservation ID or family selector, returns no executable reference for ambiguous/missing/cancelled/waitlisted/unsupported targets, and explicitly says 'This preview sends no cancellation POST.' It also mentions showing credit-loss risk at 9NBC, providing richer behavioral context beyond the annotations.

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 description is moderately long but every sentence adds value: it states the purpose, prerequisites, matching constraints, conditional behavior (credit-loss risk), required confirmation flow, and non-mutation guarantee. It is front-loaded with the core purpose and maintains a logical structure. No redundant or filler sentences.

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?

Given the output schema exists (not shown here) and annotations cover safety, the description provides sufficient context: it explains the tool's role in the cancellation workflow, prerequisites, behavioral limitations, and the confirmation requirement. It does not mention return value details, but that is likely covered by the output schema. The only minor gap is the lack of explicit per-parameter explanation, but that is a smaller concern because the schema patterns and names are clear.

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%—the properties have no descriptions—so the description must compensate. It explains that the tool matches the schedule reservation based on date, className, startTime, and endTime, and that no reservation ID or family selector is accepted, implying these four required fields are how the class is identified. However, it does not explain each parameter individually or mention the optional gymId, leaving some ambiguity for agents. The parameter names are self-explanatory, but the description could be more explicit about what gymId means (likely the gym identifier related to the IANA zone).

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?

The description states a specific verb and resource: 'read the configured account’s fresh daily schedule and prepare cancellation of one exact booked class.' It clearly distinguishes itself from execute_booking_cancellation by emphasizing that this is a preview step that sends no cancellation POST, and it names the sibling execute_booking_cancellation as the next step. This makes the tool's role unambiguous.

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 description explicitly instructs to obtain explicit account-holder confirmation before execute_booking_cancellation and notes that this preview sends no cancellation POST, establishing the correct order of operations. It also specifies a prerequisite (user-confirmed gym IANA zone) and mentions a condition at 9NBC (show credit-loss risk). However, it does not explicitly state when to use this over other prepare tools like prepare_booking_creation, though the focus on cancellation is clear enough.

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