mcp-vmwhere

列出虛擬機

list_vms

Read-onlyIdempotent

Lists vCenter VMs with computed totals for count, power state, vCPU, and memory; filter by exact or partial name and power state.

Instructions

列出 vCenter 中的虛擬機(VM),並附上算好的彙總。

回傳: total: 符合條件的 VM 台數(要回答「幾台」請直接引用,不要自己數 vms)。 power_state_counts: 依電源狀態分組的台數。 total_cpu_count / total_memory_GiB: 符合條件 VM 的 vCPU 與記憶體配置合計。 vms: 每台 VM 的 id、名稱、電源狀態、CPU 數與記憶體(MiB),依名稱排序。

參數: power_state: 選填,依電源狀態過濾。 name: 選填,VM 名稱完全比對。 name_contains: 選填,名稱包含此關鍵字(不分大小寫)。只知道部分名稱時用這個。

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_vms"
  }
}

Input Schema

Name	Required	Description	Default
`name`	No
`power_state`	No
`name_contains`	No

Output Schema

Name	Required	Description	Default
`vms`	Yes
`total`	Yes
`total_cpu_count`	Yes
`total_memory_GiB`	Yes
`power_state_counts`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover readOnly/idempotent/openWorld, so the safety profile is known. The description adds behavior beyond that: results are sorted by name, aggregates are precomputed, and the explicit directive to quote total rather than counting vms yourself — a non-obvious instruction an agent could not infer from annotations or schema.

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?

Front-loaded with purpose, then cleanly sectioned into return values and parameters. Slightly long, and the return-value block partly restates the output schema, but every line is readable and nothing is padding.

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 read-only list tool with an output schema, the definition covers what it does, all parameters, and the shape of results. The one gap is no warning about unbounded result size or how to narrow a large inventory beyond the name filters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry the full load — and it does, documenting all three parameters: power_state as a filter, name as exact match, and name_contains as case-insensitive substring. The exact-vs-substring distinction is precisely the kind of meaning the bare schema lacks.

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+resource: list VMs in vCenter, plus computed aggregates. The resource (VM) is distinct from every sibling (list_hosts, list_clusters, get_vm), so an agent can route on name and opening line alone 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?

It gives intra-tool guidance (use name_contains when you only know part of the name), which is genuinely helpful for parameter selection. However, it never mentions when to use this versus get_vm for a single VM, and gives no exclusions or scope caveats (e.g., very large inventories).

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

Deploy Server