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

Beyond the destructiveHint=true annotation, it discloses the important behavioral facts: the reason is appended to notes rather than emailed, no attendee notification goes out, and certain appointment types cannot be cancelled here and instead return manage_in_app. Those are exactly the surprises an agent needs before firing a destructive call.

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, front-loaded with the action and followed by sourcing, exclusions, and the confirmation rule in a sensible order. Slightly dense with routing detail, but nothing is filler.

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?

The output schema covers return values, and the description handles the remaining unknowns an agent faces on a destructive tool: where ids come from, what is not destroyed/notified, what happens for externally synced records, and that human confirmation precedes the call.

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% and both parameters already document their meaning and source ('uuid from list_appointments', 'appended to the appointment notes'). The description's 'optionally noting a reason' and 'Ids come from list_appointments' largely restate the schema, so this is baseline rather than added value.

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 ('Cancel an appointment') plus a scope qualifier ('on the Sales Calendar'), and explicitly bounds it ('CRM calendar only — no attendee email'). An agent can distinguish it from reschedule_appointment and from the external scheduling-link path 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?

Routes the agent to list_appointments for ids and gives a clear conditional exclusion (synced/booking-link appointments return manage_in_app). It also adds a procedural precondition ('Confirm with the member first'). It stops short of naming sibling alternatives like reschedule_appointment, so it is strong but not exhaustive.

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