mcp-vmwhere

列出 ESXi 主機

list_hosts

Read-onlyIdempotent

Lists ESXi hosts managed by vCenter with connection and power states, plus counts grouped by status. Optionally filter hosts by connection state.

Instructions

列出 vCenter 管理的 ESXi 主機,並附上依狀態分組的台數。

回傳 total(主機台數,直接引用)、connection_state_counts、power_state_counts, 以及每台主機的 id、名稱、連線狀態與電源狀態(依名稱排序)。

參數: connection_state: 選填,依連線狀態過濾。

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": "list_hosts"
  }
}

Input Schema

Name	Required	Description	Default
`connection_state`	No

Output Schema

Name	Required	Description	Default
`hosts`	Yes
`total`	Yes
`power_state_counts`	Yes
`connection_state_counts`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's extra burden is light, and it does add genuinely useful behavior: results are sorted by name, and the payload includes aggregate counts grouped by connection and power state. It does not mention pagination, result limits, or behavior for a large inventory, which keeps it from a 5.

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?

The description is front-loaded with the purpose, then the return shape, then the parameters, which is a sensible order. The return-value enumeration is somewhat redundant when an output schema exists, but that redundancy remains compact and is easy to scan.

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?

This is a simple single-parameter read tool with full annotation coverage and an output schema, so the bar for completeness is low; the description covers purpose, filtering, sort order, and aggregate fields. It could mention how missing values are handled, but nothing essential for correct invocation 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?

The schema description coverage is 0%, so the description must carry the parameter meaning; it does state that connection_state is optional and filters by connection state. The allowed values (CONNECTED, DISCONNECTED, NOT_RESPONDING) exist only in the schema enum and are not restated, and the description does not say that omitting the parameter returns all hosts.

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?

The first line states a specific verb and resource ('列出 vCenter 管理的 ESXi 主機') for a tool that sits among eight sibling list_* tools, so an agent can narrow this down to the host resource without ambiguity. The scope qualifier ('vCenter 管理') also separates it from raw hypervisor inventory.

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 description implies the usage through the resource name and the optional filter, and the sibling set makes the host-vs-VM distinction obvious. However, it never says when to prefer this over another tool, whether an empty result is normal, or what happens when connection_state is omitted (which appears to mean 'all states').

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

Deploy Server