prepare_booking_creation

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context: 'The short-lived reference does not book a class' and 'Possible credit use and the unverified balance are disclosed.' These go beyond the annotations by explaining the temporal nature of the reference and the disclosure of side effects (credit usage), which is not communicated by the annotation flags.

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 concise and front-loaded: the first sentence states the purpose and scope, followed by prerequisites, exclusions, and the required confirmation flow. Each sentence adds a distinct, non-redundant piece of information. It is not bloated but packs a lot of essential context into a short paragraph.

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 preparation tool that is part of a two-step booking flow, the description covers the core requirements: what it does, what data it needs, what it does not do (no booking, no action on ambiguous targets), and the required confirmation step before calling the sibling. The output schema exists, so explaining the return structure is unnecessary. The only minor gap is no explicit mention of error handling for invalid inputs, but the statement about ambiguous targets receiving no action covers the most likely failure mode.

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?

With schema description coverage at 0%, the description carries the burden of explaining parameters. It maps the required parameters to their roles: 'class name, date, start and end time' and 'user-confirmed gym IANA zone' for the gymId. It also emphasizes the need for exact and unambiguous values, which is essential for correct invocation. While it does not detail formats (covered by schema patterns), it does provide the semantic meaning behind each parameter, compensating for the lack of schema descriptions.

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 clearly states the tool's purpose: 'Read the current daily schedule and prepare one exact class booking for the configured account.' It distinguishes itself from the sibling execute_booking_creation by explicitly stating it does not book, and it names the exact target parameters (class name, date, start/end time). This is a specific verb+resource that tells an agent exactly what the tool does.

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 gives explicit usage context: it requires a user-confirmed gym IANA zone and exact class details, and it states that ambiguous/missing/already booked/waitlisted/unsupported targets receive no action reference. It further instructs to 'Show the full preview and obtain explicit account-holder confirmation before execute_booking_creation,' which routes the agent to the correct sibling for the actual booking. This is clear when/when-not guidance with an explicit alternative.

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