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

Annotations mark it as non-read-only, non-idempotent, non-destructive. The description adds real behavioral value beyond that: it is sandbox-restricted, only applies to bookings in awaiting_approval, and mirrors an action normally performed by the account holder. It doesn't detail failure behavior for bookings in other states.

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?

Two tight sentences with the sandbox constraint and state precondition front-loaded. Nothing is redundant or padded.

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?

An output schema exists, so return values needn't be explained. The description covers the sandbox scope and the awaiting_approval precondition, which are the key invocation prerequisites; only error/edge behavior is left implicit.

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?

One parameter with 100% schema coverage, where the schema already states the booking_id source (create or list). The description adds no syntax, format, or semantics beyond what the schema documents, so the baseline 3 applies.

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 (approve), resource (booking), and precondition (awaiting_approval), plus the sandbox-only scope. It contrasts with the live path ('Live bookings can only be approved by the account holder'), which distinguishes it from siblings like advertiser.bookings.pay or update.

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?

Makes the use case explicit: only for sandbox testing so the rest of the flow can be exercised, and clarifies that live approvals are out of scope for this tool. It does not name a sibling as an alternative, but the when/when-not condition is clear.

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