Skip to main content
Glama

Get VM performance history

proxmox_get_vm_stats
Read-only

Retrieve a VM's performance history from Proxmox RRD: CPU, memory, network and disk min/avg/max over hour to year, plus a downsampled series for trend and capacity questions.

Instructions

Get a VM's performance history from Proxmox's RRD database: min/avg/max of CPU %, memory, network and disk throughput and pressure stalls over the last hour/day/week/month/year, plus a downsampled time series. Use for 'was it busy?', trend and capacity questions.

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": {
      "vmid": "<vmid>"
    },
    "name": "proxmox_get_vm_stats"
  }
}

Input Schema

NameRequiredDescriptionDefault
cfNoConsolidation function for each data point (default AVERAGE)
rawNoReturn the full unprocessed objects from the API (larger)
nodeNoNode the guest is on. Looked up automatically from the VMID when omitted.
vmidYesVM or container ID (VMID), e.g. 100
pointsNoNumber of points in the returned series (default 12; 0 = summary only)
timeframeNoTime window (default hour)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds that data comes from the RRD database, that results are min/avg/max aggregates plus a downsampled series, and which windows are available. It omits caveats an agent might need for interpretation, such as RRD retention being coarser for longer windows, but overall it adds meaningful context beyond annotations.

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?

Two sentences with no filler: the first delivers purpose, source, metrics and return shape; the second delivers usage cues. Front-loaded and appropriately dense for the amount of information conveyed.

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?

No output schema exists, but the description tells the agent what comes back (min/avg/max per metric plus a downsampled series), which compensates well. Slightly short of 5 because nothing is said about units, series granularity limits, or what happens when the VM has no data for a requested window.

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 description coverage is 100% and two parameters are enums, so the schema already documents timeframe, cf, points, raw, node and vmid. The description reinforces the timeframe windows and hints at the downsampled series ('points'), but adds no syntax, defaults or edge-case meaning beyond the schema; 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 ('Get a VM's performance history') plus the data source ('Proxmox's RRD database'), and enumerates the metrics returned. The resource qualifier 'VM's' inherently separates it from the container, node and storage stats siblings.

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 concrete when-to-use framing: "Use for 'was it busy?', trend and capacity questions," which maps well to investigative scenarios. It stops short of naming an alternative or exclusion condition (e.g., current/live utilization vs. historical, or node-level aggregation), so it is not a full routing guide.

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