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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds genuinely new behavior — no API-level restore, side effect of patient notification governed by clinic settings. It does not state what happens on a repeat cancel (likely an error, per non-idempotent hint) or any permission requirements.

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?

Three tight sentences: mutation flag first, irreversibility and side effect second, required input and endpoint last. No filler and nothing buried.

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?

For a 3-parameter destructive tool with no output schema, it covers irreversibility, the prerequisite reason lookup, and the patient-notification side effect. Minor gaps remain around failure modes on an already-cancelled appointment and the role of the optional notes field.

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 67% and already documents reason_id's source tool and notes' purpose, so the description's reason-id sentence largely repeats structured data. It adds the 'required' emphasis but says nothing about appointment_id or when to supply notes, 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 WRITE marker and a specific verb+resource: 'cancels an existing appointment', scoping it clearly apart from feegow_create_appointment, feegow_reschedule_appointment, and feegow_update_appointment_status. The endpoint path reinforces exactly which operation is performed.

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 clear context: irreversible, so book a new appointment instead, and a reason id is required from feegow_list_appointment_reasons. It stops short of naming sibling alternatives explicitly — e.g. that feegow_reschedule_appointment moves a slot rather than killing it, or that feegow_update_appointment_status may be preferable for no-shows.

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