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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description adds real value by disclosing the cancellation-fee cost and the user-confirmation requirement, plus the underlying POST endpoint. It stops short of saying what happens to the other dropoffs in the job or any delivery-state restrictions on cancellation.

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 front-loaded sentences plus an endpoint reference, with the scope stated first and the fee warning immediately after. The API path is marginally useful grounding but not strictly needed by an agent choosing the 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, fee-bearing mutation with no output schema, the definition covers cost and confirmation but omits failure modes (invalid delivery id, non-cancellable state) and the effect on the remaining deliveries. Annotations cover the safety profile, but operational edge cases are unaddressed.

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 100%, including an enum for public_reason_key, so the schema carries parameter meaning. The description mentions none of the three parameters and adds no guidance on when a reason key or comment should be supplied; 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 with explicit scope: 'Cancels a single delivery (one dropoff) of a multi-drop job,' which implicitly separates it from stuart_cancel_job. It never names the sibling or the whole-job alternative, so the differentiation is inferable rather than stated.

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 a clear procedural precondition: 'A cancellation fee may apply; confirm with the user first,' which tells the agent to check before invoking. It offers no explicit when-not conditions (e.g., after pickup, delivery already completed) or named alternatives.

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