Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

delete_guest

Destructive

Delete a stopped Proxmox guest with all disks and snapshots, removing backups unless keep_backups is true; protected backups always remain.

Instructions

Delete a stopped guest with all its disks and snapshots — and its backups, which Proxmox would keep (protected ones always stay), unless keep_backups is true.

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>",
      "reason": "<reason>"
    },
    "name": "delete_guest"
  }
}

Input Schema

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

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?

Annotations already flag destructiveHint=true, but the description adds genuinely new behavioral facts: backups would normally be preserved by Proxmox yet are removed here, protected backups are always retained, and keep_backups overrides the default. This is exactly the kind of consequence disclosure a destructive tool needs beyond structured hints.

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 dense sentence front-loads the action and cascade, with the em-dash aside carrying the surprising backup-deletion detail. The nested clause about protected backups is slightly hard to parse on first read but every element earns its place.

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?

For a destructive, no-output-schema tool, the description covers scope, side effects, exceptions, and the override flag, which is nearly everything an agent needs. It stops short of stating irreversibility or the running-guest failure mode, which would close the remaining gap.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description goes further by explaining keep_backups' default semantics and the protected-backup exception that the schema's terse 'Keep its backups' does not convey. It does not elaborate on host or vmid 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?

States a specific verb (delete) and resource (a stopped guest) plus the cascade scope (all disks, snapshots, and backups). The cascade wording implicitly separates it from single-object siblings like delete_snapshot and delete_backup, though no alternative is named explicitly.

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 phrase 'a stopped guest' establishes an important precondition, implying the tool applies only to powered-off guests. However, there is no explicit when-to-use guidance versus delete_snapshot/delete_backup, no warning about confirming with the user, and no statement of what happens 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.