Skip to main content
Glama
Sign In
io.github.AIops-tools/proxmox-aiops

io.github.AIops-tools/proxmox-aiops

by AIops-tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

node_pressure_rca

Read-only

Rank Proxmox cluster nodes by CPU, memory, and root filesystem pressure, flagging those over thresholds worst-first and citing measured values with recommended actions.

Instructions

[READ] Rank cluster nodes by CPU / memory / root-fs pressure.

Pulls the /cluster/resources node view and flags each node over the CPU (85%), memory (90%), or disk (85%) thresholds, worst-first, citing the measured percentage and a concrete action for every finding.

Args: target: Proxmox target name from config; omit to use the default.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "node_pressure_rca"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.8.0

TDQS

A4.2/5.0
Behavior4/5

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

readOnlyHint already covers safety, and the description adds real behavioral context beyond it: the data source (/cluster/resources node view), the specific thresholds (85% CPU, 90% memory, 85% disk), the worst-first ordering, and that every finding cites a measured percentage plus a concrete action. This is richer than the annotation alone, though it stops short of describing the exact output shape.

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?

Front-loaded with the [READ] tag and the one-line purpose, then supporting detail, then args. Every sentence contributes (action, source, thresholds, ordering, output content). No filler.

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?

With no output schema, the description must convey the return shape, and it does reasonably well: it returns nodes ranked by pressure, each with a measured percentage and a suggested action. Minor gaps remain around exact field format and behavior on an all-healthy cluster, but nothing essential to correct invocation is missing.

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 description coverage is 0%, so the description must carry the single parameter, and it does: 'target' is defined as a Proxmox target name from config, with the null-omission behavior explained ('omit to use the default'). This meaningfully compensates for the empty schema.

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 (Rank) plus resource (cluster nodes) and the exact dimensions (CPU / memory / root-fs pressure). The explicit thresholds and 'worst-first' ranking distinguish it from generic siblings like node_status, node_list, and cluster_resources. An agent can tell what it produces 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 Guidelines3/5

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

The diagnostic intent (flagging over-threshold nodes) implies when it is useful, and it is clearly an RCA tool alongside guest_health_rca. However, it never states when to prefer it over node_status or cluster_resources, nor any exclusions or prerequisites. Usage is inferable but not guided.

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