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

The description goes beyond the destructiveHint annotation by disclosing that it refunds the escrow in full and that it fails once a worker has accepted, potentially while they are traveling. This gives the agent a complete picture of side effects and failure modes, with no contradiction to annotations.

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 two sentences with no fluff, front-loading the core action and then stating the key failure condition. It is easy to scan and every sentence contributes value.

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 simple one-parameter tool with destructive annotations, the description covers the action, refund, and failure condition. It does not describe the response format, but with no output schema that is acceptable. The tool is sufficiently complete for an agent to decide when and how to call it.

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?

The schema already fully documents dispatch_id as 'Id returned by errand_dispatch', and the description adds no additional parameter-specific meaning. With 100% schema coverage, the baseline of 3 is appropriate.

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 action (cancel) and resource (real-world human dispatch), and distinguishes it from sibling tools like errand_dispatch, errand_get_status, and errand_quote by specifying the cancellation and refund behavior. The condition 'while it is still open' adds precision and scope.

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 gives explicit usage conditions: it is valid only when the dispatch is still open and fails after a worker has accepted. This provides clear guidance on when to use the tool, though it does not explicitly name alternative tools. However, the sibling list makes the cancellation role obvious.

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