Delivery: cancel parcel [sandbox]

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

Annotations indicate destructive and non-idempotent behavior. The description adds that cancellation is on behalf of the receiver, returns a success status, and is limited to test parcels. It provides context beyond annotations but does not detail potential error cases or side effects like rollback.

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?

The description is concise and front-loaded with key information (sandbox, actor, success status, constraints). It efficiently differentiates from a sibling tool. Minor improvement could be breaking into shorter sentences or bullet points.

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?

Given the sandbox context, 4 parameters, and no output schema, the description adequately covers the purpose, constraints, and comparison. It leaves out details about dryRun and idempotencyKey (handled by schema) and error scenarios, but for a sandbox cancel tool this is acceptable.

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 the schema already describes all parameters. The description repeats that actor must be 'receiver' but does not add significant new meaning beyond the schema's const declaration.

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?

The description clearly states the tool cancels a test parcel on behalf of the receiver, with a specific verb and resource. It distinguishes itself from the sibling tool delivery_v1_cancel_parcel by mentioning the actor field and base contract.

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 description specifies that only parcels created via delivery_create_sandbox_parcel_v2 can be cancelled, and that it's for delivery-service partners only. It also contrasts with delivery_v1_cancel_parcel, providing clear context for when to use this tool. However, it does not explicitly state when not to use it for non-sandbox scenarios.

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