job_startLaunch a command in the background and return a job ID for later status checks or output retrieval.
Launch a command in background. Returns job_id; page with job_output, block with job_wait.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| command | Yes | ||
| timeout_seconds | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is not read-only and not destructive, covering the mutation aspect. The description adds that the command runs asynchronously and that results are retrieved via job_output/job_wait, which is useful. However, it does not disclose potential side effects, failure modes, or environment details, leaving the agent with limited behavioral awareness beyond the annotations.
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 two short sentences that are front-loaded with the primary action and then provide the return value and follow-up tools. Every word earns its place, with no redundancy or unnecessary detail.
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?
Given the presence of an output schema, the return value is partially covered, but the description omits all parameter semantics and provides minimal guidance on usage context. The tool has three parameters, and without any explanation, an agent cannot reliably construct a valid call. The description is far from complete for a tool of this complexity.
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?
The schema has 0% description coverage for all three parameters (command, cwd, timeout_seconds), and the description provides no information about them. An agent cannot infer what these parameters mean or how to set them correctly. This is a significant gap that the description fails to compensate for.
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 states a specific action ('Launch a command in background') with a clear resource and differentiates itself from foreground alternatives by emphasizing background execution. It also names the companion tools (job_output, job_wait) and the return value (job_id), giving a complete sense of what the tool does and how it fits into the workflow.
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 implies when to use the tool (for background jobs) but does not explicitly state when not to use it or mention alternatives like run_command or terminal_*. The context of 'background' and the presence of sibling tools suggests the use case, but no explicit guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.