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

Annotations already declare destructiveHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavior: a possible cancellation fee triggered once a courier is already en route, plus the under-the-hood POST /v2/jobs/{jobId}/cancel semantics. It doesn't say what happens to in-flight delivery state or what errors come back, keeping it below a 5.

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, each carrying a distinct payload: scope, cost/confirmation risk, reason-key purpose. The destructive scope lands first, before the caveats, so nothing important is 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 destructive, no-output-schema mutation this covers the essentials an agent needs: what is destroyed (the job and all deliveries), the financial risk, the confirmation gate, and parameter intent. What's missing is failure/reversibility detail — e.g. whether an already-started job can be refused — which matters given destructiveHint.

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 the enum already enumerates the reason keys, so the baseline is 3. The description adds the *why* for public_reason_key ("for reporting"), which is intent that the schema does not convey, nudging it above baseline; job_id and comment receive no extra explanation.

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?

"Cancels a whole job and all its deliveries" gives a specific verb plus resource and states the blast radius, which implicitly separates it from the sibling stuart_cancel_delivery that targets a single delivery. An agent can pick between the two without opening either 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?

It states a concrete precondition — confirm with the user first because a fee may apply once a courier is on the way — which is real usage guidance. It stops short of naming stuart_cancel_delivery as the lighter-weight alternative for a single delivery, so the when-to-use-this-vs-sibling routing is left implicit.

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