VMware-Monitor

get_host_performance

Read-onlyIdempotent

Retrieve live CPU, memory, disk, and network utilization for each ESXi host, sorted busiest first, to pinpoint hot hosts and investigate the VMs driving load.

Instructions

[READ] Real-time CPU/memory/disk/network utilisation per ESXi host.

Returns the list envelope with a real total (hosts that reported metrics). Unlike list_esxi_hosts (static config: cores, total GB) this is LIVE 20-second PerfManager data: cpu_usage_pct, mem_usage_pct, mem_consumed_mb, disk_kbps, net_kbps, busiest first. Disconnected hosts and hosts without a real-time provider are skipped, not reported as zero. Point-in-time only — no historical trend.

Use this to find which host is hot, then investigate_host to drill into it, or get_vm_performance to see which VMs on it are driving the load.

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": "get_host_performance"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max host rows to return (None = all).
`target`	No	vCenter/ESXi target from config (default if omitted).
`host_name`	No	Filter to a single host by exact name (None = all hosts).

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.2.0Oct 15, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behavioral context beyond them: 20-second sampling cadence, point-in-time only with no historical trend, disconnected or provider-less hosts being skipped rather than reported as zero, and busiest-first ordering. The 'skipped, not zero' detail is exactly the kind of edge case that prevents misreading a result.

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?

Three short paragraphs, front-loaded with the read-only marker and the resource, then the differentiating metrics, then the routing advice. No sentence is filler and each carries distinct information.

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?

There is no output schema, so the description carries the return-value burden and does it: the list envelope with a real total, the precise metric field names, and the sort order. Combined with the safety annotations and full schema coverage, an agent has everything needed to call and interpret this tool.

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%, so limit, target, and host_name are already documented in the schema, and the description adds little about them directly. It does imply ordering ('busiest first') which interacts with how limit truncates results, but that is marginal. Baseline 3 applies when the schema does the heavy lifting.

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 ('real-time CPU/memory/disk/network utilisation per ESXi host') and enumerates the exact metrics returned. It explicitly distinguishes itself from the sibling list_esxi_hosts by labelling that tool as static config versus this one as LIVE PerfManager data, so an agent can choose without opening either 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 routing: 'Use this to find which host is hot, then investigate_host to drill into it, or get_vm_performance to see which VMs on it are driving the load.' It also names the condition that rules it out in favor of list_esxi_hosts (static config vs live metrics).

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