delegate-kimi

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

The description complements annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) by explaining the sandboxed workflow, autonomy via --yolo, and that changes require caller review. It adds context not in annotations, such as the task lifecycle (start, status, collect) and safety guarantees. However, it does not detail what happens on errors or cleanup behaviors beyond the 'cleanup' parameter.

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 (~60 words) and front-loaded with the core purpose. Each sentence adds information: autonomous execution, return value, collection step, and safety. No redundant or vague statements.

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 tool with 11 parameters, multiple actions (start, status, collect), and no output schema, the description covers the basic flow but leaves gaps. It explains start and collect, but not what status returns. It omits details on progress tracking or error states. The high parameter count and complexity warrant more completeness.

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 high (82%), so the baseline is 3. The description adds some semantic value by linking parameters to the workflow (e.g., 'Returns a taskId' explains the purpose of action 'start', and 'optionally looping against a test command' relates to autoTest). However, it does not provide additional meaning beyond what the schema already gives for most parameters.

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's purpose: 'Delegate an implementation task to Kimi in an isolated git worktree.' It uses specific verbs ('delegate') and resources ('Kimi', 'isolated git worktree'), and distinguishes from siblings like 'ask-kimi' (query) and 'plan-kimi' (planning) by emphasizing autonomous execution and sandboxed changes.

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 explains when to use the tool: for autonomous implementation tasks with a test loop, and that changes are sandboxed for later review. It implicitly contrasts with interactive siblings like 'ask-kimi' or 'review-changes'. However, it lacks explicit 'when not to use' or alternative tool recommendations.

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