Starts a long-running task from a prompt so you can poll its progress or cancel it when needed.
Start a long-running task. Use task_status to poll and cancel_task to stop it.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| model | No | ||
| effort | No | ||
| prompt | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the asynchronous, long-running nature and the lifecycle (poll/stop), but says nothing about whether a task identifier is returned, cost/latency implications, permission needs, or the effect of omitting model/effort.
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?
Two short, front-loaded sentences with no wasted words; the purpose comes before the sibling routing. It is efficient rather than padded, though the brevity is part of why other dimensions suffer.
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?
A no-annotation, no-output-schema, 0%-param-coverage async mutation tool needs more than two sentences. Missing what gets started, what comes back, and how the four parameters affect execution leaves an agent under-equipped to call it 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% across four parameters, so the description must compensate, and it mentions none of them. The meaning of prompt, cwd, model, and effort (including the enum's cost/quality tradeoff) is left entirely unexplained.
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+resource ('Start a long-running task') and names the two lifecycle siblings (task_status, cancel_task), which distinguishes it from them. It doesn't clarify what kind of task or how it differs from delegate or deep_search, so it stops short of full sibling differentiation.
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 routes the agent to task_status for polling and cancel_task for stopping, which is real usage guidance. However, it gives no condition for choosing start_task over delegate or deep_search, and no prerequisites or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.