Skip to main content
Glama

job_start

Destructive

Start a long-running shell command on a server in the background and return a job id right away. Use it for anything that can take more than about a minute — package installs, builds, backups, migrations, large downloads. The job keeps running after this call returns and survives the connection closing; its output goes to a log you read with job_status. The command runs from the login user's home directory. On a Windows server the command is PowerShell.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "host": "<host>",
      "command": "<command>"
    },
    "name": "job_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesServer id (or exact name) from hosts_list
commandYesShell command to run in the background
usernameNoLogin user (defaults to the server's user, else root). Use the same one for job_status/job_stop.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and openWorldHint=true, and the description adds substantive context beyond them: the job survives the connection closing, output goes to a log consumed via job_status, the command starts in the login user's home directory, and Windows hosts run PowerShell. These are exactly the execution semantics an agent needs before firing a destructive background call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what the tool does and that it returns immediately, then layers usage threshold, lifecycle, and environment notes. Four sentences, each carrying distinct information with no repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description covers the return value (job id), where the output lives (log read via job_status), lifecycle behavior, and environment assumptions. Nothing an agent needs to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are documented structurally; the description adds real semantic value with the working directory and PowerShell-on-Windows behavior for `command`, which the schema does not state. It does not add anything new for host or username, but those are already fully specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start a long-running shell command ... in the background') and immediately gives the distinguishing outcome ('return a job id right away'). This clearly separates it from the foreground ssh_exec sibling and from job_status/job_stop.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete threshold for use ('anything that can take more than about a minute') with example workloads, and routes the agent to job_status for reading output. It never names ssh_exec as the alternative for short commands, leaving that inference to the agent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.