Skip to main content
Glama

command

Destructive

Runs a bounded shell command inside a selected VM session with no host credentials mounted, enabling isolated verification of base or candidate workspaces.

Instructions

Execute a bounded shell command inside a selected VM, with no host credentials mounted.

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": {
      "session": "<session>",
      "revision": "<revision>",
      "command": "<command>"
    },
    "name": "command"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYes
sessionYes
revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the risk profile is known. The description adds genuinely useful context beyond that: the execution is 'bounded' and runs with 'no host credentials mounted', clarifying the isolation model. It still omits what 'bounded' concretely means (timeout, output caps) and confirms nothing about the destructive effect of arbitrary shell commands.

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 front-loaded sentence with no filler; the isolation guarantee is stated alongside the action. It is arguably over-compressed for the risk level involved, but nothing is wasted.

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

Completeness2/5

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

For a destructive command-execution tool with three required, entirely undocumented parameters and no output schema, the description does too little: no timeout/output behavior, no explanation of the revision selector, no clarification of what the returned result contains. The safety-relevant fields fall back on annotations alone.

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%, so the description carries the full burden of explaining the three required parameters. It only loosely maps 'selected VM' to the session parameter and says nothing about what 'revision' base/candidate means — a critical semantic for a destructive execution tool. The command format and its sandboxed limits are also unexplained.

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 names a specific verb and resource ('Execute a bounded shell command') and scopes it to 'a selected VM', which is enough for an agent to distinguish an execution tool from siblings like read, write, export, or compare. It stops short of explicit sibling differentiation, so it lands at 4 rather than 5.

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?

Usage is only implied: an agent can infer this is the tool for running commands against a VM, and 'bounded' hints at sandbox limits. There is no statement of when to prefer it over read/write, no prerequisites, and no exclusions for what commands are disallowed.

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