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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: the 90-day time window, the authentication prerequisites, the privacy guarantee ('Never shows other customers' data'), and the specific fields returned. These details go beyond what the annotations convey and provide a richer picture of the tool's behavior without any contradiction.

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 two sentences, front-loaded with the core purpose and scope. It includes essential details (time window, fields, authentication, privacy) without any extraneous content. Every sentence earns its place, and the structure is clean and efficient.

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 there is no output schema, the description appropriately lists the returned fields and the time window. It also covers authentication and privacy. It omits mentioning that booking_reference can retrieve a single booking, but that is covered in the schema, so the agent can discover it. Overall, it provides sufficient context for an agent to call the tool correctly, though it could mention pagination or ordering, which are not critical for a simple listing.

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 description coverage is only 33% (only booking_reference has a schema description). The tool description clarifies the auth parameters by stating 'Requires customer_grant or a signed-in customer,' which implies session_id is for signed-in customers and customer_grant is for granted access. However, it does not mention the optional booking_reference parameter at all, though the schema does provide its purpose. The description adds some semantic value for the auth parameters but does not fully compensate for the low schema coverage.

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 ('Lists'), a clear resource ('the verified customer's bookings'), a scope ('from the last 90 days'), and enumerates the returned fields (reference, services, time, price, status, reschedule/cancel availability). It also distinguishes itself from siblings by emphasizing that it never shows other customers' data, which sets it apart from any general listing or mutation tools like cancel_booking or reschedule_booking.

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 implies usage for retrieving the current customer's bookings and notes the authentication requirement (customer_grant or signed-in customer), but it does not explicitly contrast with alternatives such as cancel_booking or reschedule_booking, nor does it state when not to use this tool. The context is clear but the guidance is implied rather than explicit.

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