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

Annotations cover the safety profile (destructive, not read-only), and the description layers on the concrete behaviors an agent actually needs: the PENDING→CANCELLED transition, the recorded rejectedAt/reason, a conflict on non-PENDING input, a side effect (emails the carrier), irreversibility ('Final: can't be undone'), and the required scope (appointments:write, Scheduler role or above). This goes well 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?

Front-loaded with the core action and state change, then routing, side effects, irreversibility, and auth in a tight sequence. Every sentence carries distinct operational information; nothing is padding.

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?

With no output schema, it still tells the agent what comes back ('Returns the updated appointment') and covers preconditions, error behavior, side effects, reversibility, and required scope. An agent has everything needed to invoke it correctly.

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 100%, so both parameters are already documented, including that reason is stored as rejectionReason. The description repeats the recording behavior but adds no format, length, or validation detail beyond the schema, so 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 precise verb (turn down), resource (a PENDING booking request) and the resulting state change (becomes CANCELLED with rejectedAt and reason recorded). It explicitly names the sibling it is not (cancel_appointment), so an agent can distinguish it from the adjacent cancellation tool without opening either 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 an explicit precondition ('Only for PENDING; otherwise conflict') and a direct routing rule: use this, not cancel_appointment, when declining a request; use cancel_appointment for an already CONFIRMED appointment. Both the when and the when-not are stated, with the alternative named.

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