Start a session Worker to run a delegated task; provider, model, and permission settings are managed by the human Worker panel.
Start the operator-configured Worker for this session. Provider, model, reasoning, access and renewal policy are intentionally not arguments; the human Worker panel owns them.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| task | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations give readOnlyHint=false, so the mutating nature is already declared. The description adds real context by stating the worker is 'operator-configured' and that provider/model/access/renewal are deliberately not arguments. It does not disclose auth requirements, side effects of starting (resource consumption, session state), or what happens if a worker is already running.
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 tightly written sentences with the core action front-loaded and no filler. The second sentence is slightly dense but earns its place by preventing misuse of non-arguments.
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 state-mutating lifecycle tool with no output schema and 0% schema description coverage, the description is thin: it neither explains the parameters nor what starting returns or guarantees. An agent knows roughly why to call it but not how to populate the required '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% for both parameters, and the description compensates only by telling the agent what is NOT an argument. Neither 'task' (the required payload) nor 'cwd' is explained, leaving the most important parameter undocumented.
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 and scope: 'Start the operator-configured Worker for this session.' This separates it from sibling lifecycle tools like worker_steer/worker_cancel/worker_wait. It does not, however, explicitly name which sibling to use instead or contrast its lifecycle position.
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 action (start a worker), and the description usefully rules out passing provider/model/renewal config, telling the agent these are owned by the human Worker panel. There is no explicit 'use this when/when not' or reference to alternatives such as worker_steer for an already-running worker.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.