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

With no annotations at all, the description carries the full burden and does disclose real behavioral traits: the visit 'stays on record with the reason' (soft cancel, not deletion) and unsent customer notices are 'dropped' (an irreversible side effect). It omits permission requirements and any externally visible notification outcome beyond the notice drop.

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?

Two sentences, both front-loaded with the operative facts: eligibility states first, side effects second. No filler and nothing repeated from the schema.

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 two-parameter mutation with no annotations and no output schema, the description covers the essentials: eligible states, retention behavior, and the dropped-notice side effect. The remaining gap is the undrawn boundary with visits_cancelSeries and unstated return/error behavior.

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 0%, so the description must compensate. It explains what 'reason' becomes on the record, which is genuinely additive, but says nothing about whether reason is optional (it is, per the schema) or that visit_id is a UUID identifying the single visit rather than the series.

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?

Names a specific verb (cancel) and resource (visit) and narrows the eligible states to 'scheduled, on the way, or arrived'. It does not differentiate from the sibling visits_cancelSeries, so an agent cannot tell from this text whether a whole series is cancelled or just the one visit.

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?

The state list ('scheduled, on the way, or arrived') implicitly tells the agent when cancellation applies, which is useful. It never mentions the alternative visits_cancelSeries or any prerequisite, and does not say what happens if the visit is in another state, so the guidance is implied rather than stated.

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