run_task

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

With readOnlyHint=false and openWorldHint=true already signaling a mutating external operation, the description adds valuable behavior: asynchronous execution returning taskId, automatic verify/rework capability, and pre-send validation of ZCode path references in task/context. 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 compact and front-loaded: the core function and async result appear first, followed by platform-specific parameter rules and a validation note. Every sentence adds information without redundancy.

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 0% schema-level explanations, this description is not complete enough. The output schema helps with return values, but the agent still lacks semantic guidance on most parameters required to configure a task correctly.

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% and there are 13 parameters, but the description only clarifies model, mode, and path-reference validation in task/context. It does not explain agentId, planDoc, autoVerify, autoFixRounds, taskTimeoutMs, reasoningLevel, designSystem, projectPath, or allowCreateProject, leaving the agent to guess for the majority of inputs.

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 names a concrete action ('启动外部 AI-Agent 开发任务') and a distinctive outcome ('异步返回 taskId'), going well beyond the bare title. This clearly separates a launch/dispatch operation from sibling tools like continue_task, query_task, or rework_task.

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?

Usage is implied by the core phrasing '派活' and '启动外部 AI-Agent 开发任务', but the description does not explicitly state when to choose run_task over a sibling such as continue_task or rework_task. The platform-specific model/mode rules are useful configuration guidance but are not tool-selection guidance.

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