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

Goes well beyond the annotations: states the slot is freed, that Appointo may notify customers, that Shopify refunds are outside this call's control, that it is irreversible through this server, and that the docs cap it at 100 requests/day. These are exactly the side-effect and quota facts an agent needs before invoking a destructive tool.

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?

Four short sentences, each carrying distinct information (mode, scope, side effects, irreversibility, quota, endpoint) with the WRITE marker and scope front-loaded. No filler or repetition.

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?

Covers destructive side effects, quota, and non-idempotent consequences for a tool with no output schema; only the shape of the response (e.g. what the cancelled booking record looks like) is left unstated, which is a minor gap for a cancel operation.

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 coverage is 100%, so booking_id provenance and the customer_ids partial-cancel semantics are already fully documented in the schema. The phrase 'or only some of its customers' mirrors rather than extends 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?

Opens with an explicit mode marker (WRITE) plus a specific verb and resource: cancel a booking, or a subset of its customers. The full-vs-partial distinction is stated up front and the endpoint (PUT /bookings/cancel) identifies the exact operation, so it is trivially separable from siblings like reschedule_booking or list_cancelled_bookings.

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?

Clearly says this cannot be undone and directs the agent to create a new booking instead, which is a genuine when-not/alternative statement. It does not explicitly compare against appointo_reschedule_booking or note the preconditions for a partial customer cancel, so it falls just short of a full routing rule.

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