cancel_task

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

With no annotations, the description carries the full burden and does so well: it discloses the state-machine preconditions, the financial consequences (never-paid bounty voided, escrowed deposit refunded to the payer's wallet), and the auth requirement (keypair auth). These are non-obvious effects an agent could not infer from the schema.

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 sentences, each front-loading the critical constraint: eligibility first, financial outcome second, auth last. No filler, and no sentence merely restates the tool name.

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, unannotated mutation tool with no output schema, the description supplies everything needed to call it correctly: eligibility gates, the sibling dependency, side effects on funds, and the auth requirement. Nothing material is missing.

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% for the single task_id parameter, so the schema already documents the input fully. The description adds no syntax or format detail beyond that, making the baseline 3 appropriate for a one-param tool.

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 (cancel) and resource (task), scoped to 'a task you created'. This cleanly separates it from siblings like dispute_task, accept_deliverable, and request_revision, which act on the same task objects at different lifecycle stages.

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?

Explicitly enumerates when cancellation is allowed (open, claimed, or delivered but only after dispute_task) and when it is not (accepted work, tasks with a payment in flight). The condition that routes to the dispute_task sibling is named, so the agent knows the required prior step.

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