Skip to main content
Glama
Sign In
pvewarden

pvewarden

by matousfiser
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

rollback_snapshot

Destructive

Restore a tagged Proxmox guest to a pvewarden snapshot and start it, discarding all changes made since that snapshot. Use only after explicit user request and client confirmation.

Instructions

Roll a guest back to a pvewarden snapshot and start it (requires tag 'pvewarden-update'). DISCARDS ALL CHANGES made since the snapshot, including application data. Use only when the user explicitly asks for it. Get the snapshot name from list_snapshots. If the guest had to be started, waits until it answers again (back_online), like reboot_guest. pvewarden asks the user to confirm in the client; if they decline, nothing changes.

Input Schema

NameRequiredDescriptionDefault
vmidYesProxmox VMID of the guest, e.g. 101 (see list_guests).
snapshotYesSnapshot name as list_snapshots shows it. pvewarden snapshots are named pvewarden_YYYYMMDD_HHMMSS (UTC); only those can be used here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / snapshot / description
      Added value: +"Snapshot name as list_snapshots shows it. pvewarden snapshots are named pvewarden_YYYYMMDD_HHMMSS (UTC); only those can be used here."
    • addedInput schema / properties / vmid / description
      Added value: +"Proxmox VMID of the guest, e.g. 101 (see list_guests)."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the destructiveHint annotation by naming what is destroyed ('ALL CHANGES... including application data'), the tag prerequisite, the confirmation prompt flow, and the post-rollback wait-until-online behavior. The 'nothing changes if declined' note clarifies failure semantics that annotations cannot express.

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?

Purpose is front-loaded, immediately followed by the destructive-warning capitalized for scanning, then the precondition and the post-condition behavior. No sentence is filler; each carries a distinct operational fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive two-parameter mutation with no output schema, the description covers destruction scope, prerequisites, user consent flow, and the long-running wait semantics. Nothing an agent needs in order to call this correctly or warn the user is missing.

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 both parameters are already documented in the schema with the same naming convention (pvewarden_YYYYMMDD_HHMMSS) and vmid lookup hint. The description's pointer to list_snapshots adds workflow value but little parameter meaning beyond what the schema provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Roll a guest back to a pvewarden snapshot and start it') and embeds the qualifier that distinguishes it from sibling tools such as snapshot_guest, delete_snapshot, and reboot_guest. The agent can tell exactly what the tool does without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit conditions: only when the user explicitly asks, only for pvewarden snapshots (tag prerequisite stated), and points to list_snapshots as the source of the snapshot name. It also explains that the client-side confirmation is the user's safety gate, and that declining leaves state unchanged.

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

Deploy Server

Other Tools