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

Goes far beyond the destructive/idempotent/openWorld annotations: it discloses cascading deletion of all rides behind the same Confirm link, that unconfirmed and unpaid requests are cancelled instantly with an email, and that paid bookings become an operator-handled request with concrete refund rules (deposit back >24h before pickup, 25% kept inside 24h). This is exactly the consequence information an agent needs before 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?

Front-loads the core action, then branches into the three outcome cases (unconfirmed / unpaid / paid) before the parameter and confirmation notes. Dense but nearly every clause carries a distinct behavioral fact; the refund detail is a long parenthetical but justified for a destructive tool.

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 no output schema, it covers outcomes (email sent, cancellation passed to the operator) and the refund policy. What it does not state is what the tool returns to the caller or whether cancellations are reversible once passed to the operator.

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 email, bookingId and the optional reason are fully documented in the schema. The description only restates the two required inputs and omits the optional `reason`, adding no meaning beyond the structured fields. 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 a specific verb+resource ("Cancels a ride") plus the precondition "at the customer's explicit request," which separates it cleanly from change_booking and get_booking_status. An agent can pick this out of the sibling list without opening a 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?

States the triggering condition (customer's explicit request) and gives an operational instruction: "Ask the customer to confirm before calling." It never names change_booking as the alternative when the customer merely wants a modification, so the exclusion is only implied.

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