run_task

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, indicating a mutating operation with side effects. The description adds context that the task runs externally, returns asynchronously, includes auto-acceptance/rework, and validates ZCode project path references before sending. This adds meaningful behavioral context beyond annotations, though it does not disclose failure modes or resource consumption.

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 compact, with the core purpose front-loaded in the first clause ('启动外部 AI-Agent 开发任务并可自动验收返修，异步返回 taskId'), followed by provider-specific details and a validation note. The structure is efficient with no redundancy, though it could be broken into clearer sentences for readability.

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 13 parameters and no output schema, the description is incomplete. It does not explain return value details beyond taskId, does not mention how to fetch results (e.g., via get_task_report), and leaves many parameter semantics unexplained. The provider-specific guidance helps but does not make the tool fully usable without additional documentation.

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 description coverage is 0%, so the description must compensate. It explains model and mode semantics for both providers (required vs optional, mode support), and mentions path validation for task/context. However, it leaves many parameters (autoVerify, autoFixRounds, taskTimeoutMs, reasoningLevel, allowCreateProject, planDoc, designSystem, agentId) undocumented, providing only partial compensation for the schema gap.

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 launches external AI-Agent development tasks with auto-verification and rework, returning taskId asynchronously. The verb 'launch' plus resource 'external AI-Agent development task' makes the core action explicit. It does not explicitly differentiate from sibling tools like continue_task or rework_task, but the launch/dispatch nature is evident from the wording.

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 provides provider-specific guidance (ZCode vs TraeWork) for parameter values but does not explain when to use this tool versus alternatives such as continue_task or rework_task. There is no mention of prerequisites or conditions that would select this tool over a sibling, leaving tool-selection guidance entirely implicit.

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