Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

edit_backup_job

Destructive

Modify settings of a Claude-created Proxmox backup job, including schedule, retention, guests, storage, and enabled status, without touching the user's own jobs.

Instructions

Change a backup job Claude made (ID claude-…): any of its settings, or enabled to turn it off and on. keep {} goes back to the storage's own rule; a keep with numbers needs the Destroy switch (see create_backup_job). The user's own jobs cannot be changed here.

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>",
      "id": "<id>",
      "reason": "<reason>"
    },
    "name": "edit_backup_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
allNoEvery guest of the host (but those in exclude).
hostYesThe host's id, from list_hosts.
keepNoHow many backups to keep (Destroy switch).
modeNo
notesNoEach backup's note: {{guestname}} and {{vmid}} are filled in.
vmidsNoThe guests it backs up.
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.
commentNo
enabledNo
excludeNo
storageNo
compressNo
scheduleNoWhen: 03:00 · mon..fri 21:30 · sat,sun 02:00 · sun 04:00 · a Proxmox calendar event.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false; the description adds that 'keep {}' reverts to the storage's own rule while numeric keep values require the Destroy switch, clarifying exactly where destruction happens. It also notes the reason value is shown in an approval window and log. It does not say whether a change is reversible or what happens on partial edits.

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?

Four dense sentences, front-loaded with the action and scope before the edge-case rules. Slightly compressed phrasing ('any of its settings, or enabled to turn it off and on') costs a little readability but nothing is wasted.

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 14-parameter mutation tool with no output schema, the description covers the destructive and semantic traps an agent most needs to know. The remaining gap is the un-enumerated tuning params, though enums and the schedule format are carried by the schema.

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?

Coverage is only 50% across 14 params, so the description must compensate, and it does for the riskiest ones — the keep sub-object semantics and enabled as an off/on switch. It says nothing about mode, compress, all, exclude, vmids or storage beyond their names, leaving several params thin.

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 ('Change a backup job') and narrows scope twice: only jobs Claude made ('ID claude-…') and any of its settings or the enabled toggle. That distinguishes it from create_backup_job, delete_backup_job and run_backup_job without needing their schemas.

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?

Explicitly says the user's own jobs cannot be changed here, which is a real when-not condition, and points to create_backup_job for the keep/Destroy-switch rule. It does not say what to use instead for user-owned jobs, so it stops short of full alternative routing.

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