Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

bulk_power

Start multiple Proxmox guests in boot order or shut them down in reverse order as one task, matching the web UI's Bulk Actions.

Instructions

Start several guests one after the other in their boot order, or shut them down in reverse order — one Proxmox task, like the web UI's Bulk Actions.

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>",
      "action": "<action>",
      "vmids": "<vmids>",
      "reason": "<reason>"
    },
    "name": "bulk_power"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesThe host's id, from list_hosts.
vmidsYes
actionYes
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.
timeout_sNoShut down: how long each guest may take (default 180).
force_stopNoShut down: stop those still running after the timeout (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations declare the safe-ish profile (destructiveHint=false, idempotentHint=false) and the description adds genuinely new behavior: it is one Proxmox task executed sequentially in boot order. It does not disclose what happens on partial failure (does a failed start abort the rest?), whether the call blocks until completion or returns a task handle, or that shutdown escalates to a force stop.

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?

One front-loaded sentence, zero waste, with the ordering semantics placed ahead of the Bulk Actions analogy. Nothing redundant is restated from schema or annotations.

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?

A mutation tool with six parameters, four required, no output schema, and no annotation coverage of failure modes. The description adequately frames purpose and ordering but leaves the agent without information about return value (task id?), blocking behavior, or partial-failure handling — material for a bulk destructive-ish operation.

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 67%, and the description adds meaning to the action parameter (boot order for start, reverse for shutdown). It says nothing about vmids ordering semantics, the reason field's approval-window visibility (documented in schema), or timeout_s/force_stop, which the schema already describes.

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?

States a specific verb and resource — start several guests in boot order or shut them down in reverse — and identifies it as a bulk, single-task operation analogous to the web UI's Bulk Actions. The bulk/sequenced scope implicitly separates it from the singular guest_power sibling, though that sibling is never named.

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?

The description conveys when this tool applies (multiple guests, sequenced start or reverse-order shutdown) and the action enum is visible in the schema. It gives no explicit when-not guidance, e.g. 'use guest_power for a single guest' or prerequisites such as quorum/cluster requirements.

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