Skip to main content
Glama
Host Process & Sub-Agent Governor

Host Process & Sub-Agent Governor

by jasonroject

host_exec_start

Launch local executables in the background as detached processes, specifying arguments, working directory, priority, and timeout to supervise long-running host tasks.

Instructions

Spawn a software process running locally on the host machine in the background.

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": {
      "command": "<command>"
    },
    "name": "host_exec_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoWorking directory. Defaults to current workspace.
tagNoOptional human-readable label or purpose for this process.
argsNoCommand-line arguments.
commandYesThe executable or command to run (e.g. "npm", "python", "docker", "cargo").
priorityNoTask scheduling priority (low, normal, high, critical).
timeoutMsNoExecution timeout in milliseconds. If exceeded, automatically terminates.
allowShellNoWhether to execute within a shell (cmd.exe or /bin/sh). Defaults to false for injection safety.
spillToFileNoSpill output to temporary disk file to protect memory on large builds.
logBufferSizeNoMax stdout/stderr lines to buffer in memory (default: 2000).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. "In the background" usefully signals non-blocking semantics, but for a tool that executes arbitrary code on the host it says nothing about permissions, safety implications, what handle or identifier is returned for later lifecycle calls, or how buffered output relates to the sibling log tools.

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

Conciseness4/5

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

One front-loaded sentence with zero filler; the core purpose is the first thing read. It is arguably too thin for a nine-parameter process spawner, but nothing in it is redundant.

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

Completeness4/5

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

This is the weak point: a high-complexity tool (nine parameters, no output schema, no annotations, a whole sibling lifecycle family) is covered by a single sentence that omits returned identifiers, output retrieval, and interaction with host_exec_logs/status/stop.

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

Parameters3/5

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

Schema description coverage is 100%, and the schema already documents all nine parameters including cwd, args, allowShell, timeoutMs, and logBufferSize. The description adds no meaning beyond the schema, so the baseline of 3 applies.

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

Purpose4/5

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

The description pairs a specific verb ("Spawn") with a specific resource ("a software process running locally on the host machine") and adds a scope qualifier ("in the background"). This clearly sets it apart from the logs/status/stop siblings, though it never names those siblings or states the relationship explicitly.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no prerequisites, and no routing to alternatives such as host_exec_logs, host_exec_input, host_exec_status, or host_exec_stop. Beyond the bare statement of purpose, an agent must infer the entire process-lifecycle workflow on its own.

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