Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

restore_backup

Destructive

Restore a Proxmox guest backup as a new guest or replace an existing stopped guest; deleted guests return with their original ID and MAC when available.

Instructions

Restore a guest's backup as a new guest — or over the guest itself (replace: true; it must be stopped, and that is a Destroy request). A guest deleted since (its backup found by list_backups with its old ID) comes back as itself: its old ID while free, its old MAC.

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>",
      "vmid": "<vmid>",
      "volid": "<volid>",
      "reason": "<reason>"
    },
    "name": "restore_backup"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesThe host's id, from list_hosts.
vmidYesThe guest's ID (VMID).
startNo
volidYes
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.
replaceNo
storageNo
new_vmidNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the annotations, which only say destructive/non-idempotent. It discloses that replace is effectively a Destroy request, that the guest must be stopped, and that identity is preserved (old ID while free, old MAC) when restoring a deleted guest — exactly the consequences an agent needs before committing.

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?

Two dense sentences with the destructive path flagged parenthetically in the first and the identity outcome front-loaded in the second; nothing is wasted, though the compressed phrasing ('its old ID while free') asks the reader to parse carefully.

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 destructive 8-parameter mutation with no output schema needs thorough disclosure; the description covers the biggest risk (replace = destroy) and identity behavior, but leaves the effect of start and storage and the use of new_vmid unspecified, so an agent must still infer part of the blast radius.

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?

With only 38% schema coverage over 8 parameters, the description carries real weight and does explain replace and the ID/MAC outcome, but start, storage, volid, and new_vmid are left to the bare schema types, so several parameters remain semantically opaque.

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 (restore a guest's backup) and immediately branches into the two concrete modes: as a new guest, or over the guest itself with replace: true. An agent can tell this apart from delete_guest or clone_vm, though no sibling is named explicitly as the alternative.

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

Usage Guidelines4/5

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

Gives a clear decision rule for the main fork (default = new guest; replace: true = overwrite the guest, which must be stopped), plus the special case of restoring a guest deleted since the backup. Missing an explicit 'do not use when' clause and does not name the tool to use instead if the guest is running.

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