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

Annotations establish the safety profile (not read-only, destructive, idempotent, open-world), and the description adds substantial context beyond that: the booking stays unconfirmed until code entry or payment, repeated calls with the same checkout return the same reservation, and consent questions must be asked individually. That directly supplements the idempotentHint and destructiveHint rather than repeating them.

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 content is dense but each sentence carries operational value: consent conditions, confirmation flow, idempotency, disclosure requirements and an example. The main drawback is front-loading: it opens with a long prepositional 'Use only after...' clause, so the actual purpose appears mid-sentence rather than first.

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 complex tool with 7 parameters, nested objects and an output schema, the description covers the critical preconditions, confirmation mechanics, idempotency and a worked example. The remaining gap is guidance on the optional invoice, market, comment and accept_changes parameters, which is only partially covered by the output schema and annotations.

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 only 14% top-level schema description coverage, the description partially compensates by showing an example payload that maps the customer and consents fields. However, it says nothing about the optional parameters market, comment, invoice or accept_changes, so an agent must still infer their purpose from the schema alone.

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: 'creates the reservation from checkout_id with the driver's details.' It also distinguishes the tool from confirm_reservation_code by noting the booking is not confirmed until that step or payment, so an agent can place it in the flow 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 explicit when-to-use conditions: only after the user explicitly asked to book and, in a separate question, accepted terms/privacy and answered about marketing, with the precise clarification that a yes to booking is not a yes to terms. It also names the sibling alternative for confirmation (confirm_reservation_code) and requires showing price, deposit and cancellation policy beforehand.

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