Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

rollback_snapshot

Destructive

Roll a Proxmox guest back to a chosen snapshot, discarding any changes made after it. Use it to undo failed updates or configuration errors.

Instructions

Roll a guest back to a snapshot (what came after it is lost).

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>",
      "snapshot": "<snapshot>",
      "reason": "<reason>"
    },
    "name": "rollback_snapshot"
  }
}

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.
snapshotYes

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 already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered and the bar is lower. The description earns some credit for specifying the semantics of destruction (state after the snapshot is discarded), but it does not say whether the snapshot itself survives, whether the guest must be stopped, or what a failed rollback leaves behind.

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?

A single front-loaded sentence with the destructive consequence placed immediately after the action, so an agent sees the risk before it commits. Nothing is redundant and nothing needs trimming.

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?

For an irreversible, non-idempotent mutation with no output schema, this is adequate but thin: it conveys the core effect and the data loss but omits whether the target snapshot is consumed, whether the action can be retried safely, and any preconditions. The approval-window behavior of the `reason` argument is handled in the schema rather than the description, which is acceptable.

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 75%, so most parameters are already documented, and the description adds no format or constraint detail beyond them. The one undocumented parameter, "snapshot", is only indirectly covered by the phrase "roll a guest back to a snapshot", leaving it unclear whether it takes a name or an identifier.

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?

"Roll a guest back to a snapshot" pairs a specific verb (rollback) with the exact resource (guest snapshot) and adds the consequence clause, so an agent can distinguish it from take_snapshot or delete_snapshot without opening a schema. It stops short of naming any sibling explicitly, which keeps it from a 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?

The parenthetical "what came after it is lost" implicitly signals that this is a last-resort recovery action rather than routine snapshot management, which is useful guidance. However, there is no explicit statement of when to prefer it over alternatives or prerequisites such as the snapshot needing to already exist.

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