Skip to main content
Glama

run_command

Destructive

Executes only exact allowlisted, shell-free commands in a specified working directory with an optional timeout, enabling permission-gated local jobs in approved workspaces.

Instructions

Run only an exact allowlisted shell-free command; disabled by default

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>",
      "cwd": "<cwd>"
    },
    "name": "run_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdYes
commandYes
timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=false, so the risk profile is known. The description still adds real value by disclosing that execution is allowlist-gated, shell-free (no pipes, redirection, or globbing), and disabled by default. It does not say what output is returned or what happens on a non-allowlisted command.

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?

A single compact sentence with the most important constraint (allowlist/shell-free) and the availability gate front-loaded. No wasted wording, though the terseness borders on under-specification for a destructive executor.

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

Completeness3/5

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

Given a destructive command executor with no output schema and zero parameter descriptions, the definition covers the safety gate but omits timeout behavior, working-directory meaning, and return/failure information an agent needs to call it reliably. Adequate as a first-line warning, incomplete as a full specification.

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

Parameters2/5

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

Schema description coverage is 0% for all three parameters. The description constrains the form of 'command' (exact, allowlisted, shell-free) but says nothing about 'cwd' semantics or what 'timeout_seconds' defaults to and how expiry is handled, leaving two parameters entirely undocumented.

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 gives a specific verb and resource ('run ... command') plus two qualifying constraints: the command must be exactly allowlisted and must be shell-free. This is clearly a process/command executor, distinguishable from GUI-oriented siblings like gui_click or browser_fill, though it never names a sibling to route against.

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

Usage Guidelines3/5

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

'Run only an exact allowlisted shell-free command' implies the precondition for use, and 'disabled by default' signals the tool may be unavailable. However, it gives no explicit guidance on when to prefer this over run_job, or what an agent should do when the call is rejected.

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