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

Annotations already declare destructive=true, readOnly=false, and non-idempotent. The description adds material context beyond them: cancellation validity is bounded by the clinic's notice period, and 'Nothing is refunded here; a paid visit is settled by the clinic' answers the obvious money question. It does not mention what happens on a repeat call despite idempotentHint=false.

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 short sentences, front-loaded with the action, and every clause carries information (prerequisite, human confirmation, notice window, refund behavior). The phrasing 'the contact_proof confirm_with_code gave' is slightly compressed but still parseable.

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 destructive, open-world mutation with an output schema and full annotation coverage, the description supplies the missing operational pieces: the sibling dependency, the human-confirmation step, and the no-refund outcome. Minor gaps remain around failure behavior outside the notice window, which the output schema likely absorbs.

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 already documents booking_id, contact_proof (with its one-hour lifetime), locale, and reason. The description only restates that contact_proof comes from confirm_with_code and says nothing new about locale or reason, 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 and resource ('Cancel one of the person's bookings') plus the credential it needs and the constraint it operates under ('within the clinic's cancellation notice'). It is clearly separable from siblings like confirm_with_code and find_my_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?

Gives real routing guidance: the agent must first call confirm_with_code to obtain contact_proof, and must 'Ask the person to confirm first' before invoking. It implies the notice-window precondition but never states what to do when the window has passed, so the when-not case is left implicit.

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