Cancel a job (free)

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

The description reveals how the cancellation works (graceful shutdown, force-kill, worktree teardown), the consequence that cancelled jobs cannot be resumed, cleanup warnings for leftover paths, idempotency, and cost. This goes well beyond the annotations, which only state idempotentHint=true and offensiveHints. No contradiction with annotations exists.

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 front-loaded with the core purpose and then provides structured, spaced sentences for behavior, cleanup warnings, idempotency, and cost. Every sentence adds value without redundancy, achieving a balance of detail and brevity.

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?

The description fully explains the tool's side effects, idempotency, and output-related details (cleanup_warnings). With an output schema present, there is no need to list return values. Coverage of parameters is complete via schema, and the behavioral details make the tool's usage and consequences clear.

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 provides 100% coverage for both parameters with detailed descriptions (e.g., job_id provenance and workspace_root fallback behavior). The tool description does not add additional parameter-specific semantics, so the baseline score 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 opens with a specific verb and resource: "Cancel a running background Kimi job." It clearly distinguishes itself from siblings like kimi_job_status (status only) and kimi_job_result (result retrieval) by focusing on cancellation and its side effects.

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 implies when to use the tool by describing its behavior and stating that already-terminal jobs are returned unchanged, making it safe to retry. It also notes the tool is free, which is a cost-oriented usage consideration. However, it does not explicitly name alternatives or state when not to use it beyond the idempotency note.

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