Skip to main content
Glama

Start, stop or reboot

power_vm

start, shutdown (clean ACPI), reboot, or stop (hard power-off). Returns an action to poll with get_action. Scope: vms.action.

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": {
      "vm": "<vm>",
      "type": "<type>"
    },
    "name": "power_vm"
  }
}

Input Schema

NameRequiredDescriptionDefault
vmYesMachine id, as returned by list_vms or create_vm.
typeYesstart powers on; shutdown asks the system to stop cleanly (ACPI); reboot restarts; stop cuts the power at once, unsaved data may be lost.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / type / description
      Added value: +"start powers on; shutdown asks the system to stop cleanly (ACPI); reboot restarts; stop cuts the power at once, unsaved data may be lost."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Adds real behavior beyond annotations: the call is asynchronous and returns an action handle to poll via get_action, and the required OAuth scope (vms.action) is disclosed. It also warns that stop cuts power immediately with possible unsaved data loss, which is meaningful context. Note a mild tension: destructiveHint=false while the description says stop 'may lose' unsaved data — defensible since power-off is reversible, but worth flagging.

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?

Two tight sentences: the action list is front-loaded, followed by the return-handling hint and scope. Nothing wasted, no redundancy.

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?

No output schema exists, but the description compensates by explaining that the return value is an action to be polled with get_action. Scope/authorization is stated. The only gap is the absent contrast with destroy_vm, which matters for a destructive-adjacent power tool.

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 coverage is 100% and the 'type' enum already documents each action's semantics, including the ACPI/data-loss distinction, so the description largely restates schema content. Baseline 3 is appropriate; it adds no format or constraint detail beyond the schema.

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?

Names the four specific operations (start, shutdown, reboot, stop) rather than a vague 'manage power' — an agent can map intent to action type immediately. The resource itself (VM) is carried by the tool name and the 'Scope: vms.action' string rather than stated in prose, so it's clear but not fully self-contained.

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?

Implied usage is strong — the four action names map to obvious intent — but there is no explicit when-to-use versus when-not guidance. Notably it never distinguishes 'stop' (hard power-off) from the sibling destroy_vm, which is the most likely agent confusion for this tool family.

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.