Launch a long-running shell command in the background and get its process_id and pid for later management. Use it to run servers, watchers, or tasks without blocking the terminal.
Start a long-running background process. Returns process_id and pid.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Working directory (default: home) | |
| env | No | Additional environment variables | |
| command | Yes | The shell command to start |
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 behavioral burden. It usefully discloses that the call returns process_id and pid (the handles needed for poll_output/kill_process), but says nothing about the process lifecycle, whether it survives session teardown, how output is retrieved, or concurrency/resource limits.
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 sentences, zero filler, and the essential capability plus return values are front-loaded. Nothing needs trimming and nothing is buried.
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 spawn tool with no annotations and no output schema, the description covers the bare essentials by naming the returned handles. It omits the follow-up workflow (read_output / poll_output / kill_process) that an agent needs to actually use the started process, leaving a real gap.
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 100%, so the schema already documents cwd, env, and command. The description adds nothing beyond the schema (no mention of shell semantics, env merging behavior, or cwd defaulting), so the baseline 3 applies.
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 verb ('Start') and resource ('long-running background process'), and the 'background' qualifier implicitly separates it from the synchronous sibling run_command. It stops short of explicitly naming that alternative, so an agent must infer the boundary rather than read it.
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 only implied by the phrase 'long-running background': an agent can guess this is for work that must not block or outlive a single call, but there is no explicit when-to-use, no when-not-to-use, and no mention of run_command or run_sequence as the alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.