Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

console_send

Types text into a running Proxmox guest console and presses keys such as Enter, Tab, arrows, or Ctrl+Alt+Delete, with ordered steps for mixed input.

Instructions

Type text into a running guest's console and/or press keys: enter, tab, escape, backspace, delete, arrows (up, down, left, right), home, end, pageup, pagedown, f1–f12, and combinations such as ctrl+alt+delete or ctrl+c. Text is typed as on a US keyboard. With text and keys, the text is typed first and the keys pressed after it (type a command, then enter). For another order — keys first, or several of each — give steps instead, done in their order: for example [{"keys": ["ctrl+l"]}, {"text": "example.org"}, {"keys": ["enter"]}].

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": {
      "host": "<host>",
      "vmid": "<vmid>",
      "reason": "<reason>"
    },
    "name": "console_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesThe host's id, from list_hosts.
keysNo
textNo
vmidYesThe guest's ID (VMID).
stepsNoIn order; each either {"text": "…"} or {"keys": ["…"]}. Instead of text and keys.
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: keys are sent as on a US keyboard, and text-then-keys ordering is fixed unless steps is used. It omits what happens if the guest is not running or the console is not attached, which is the main remaining behavioral gap.

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 most important information — what it types and the key list — is front-loaded, and the ordering rule follows immediately. The inline JSON example earns its space by disambiguating steps. It is slightly dense in the key enumeration but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six parameters, no output schema, and an approval flow implied by the reason parameter, the description covers input semantics well. What it does not cover is the operational envelope: prerequisite that the guest be running/console attached, and what the call returns or how failures surface. That leaves a moderate gap for a tool with real side effects.

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 coverage is 67%, and the two undocumented parameters (keys, text) plus the steps alternative are exactly what the description elaborates, including accepted key names, layout, ordering, and the fact that steps replaces text/keys. host, vmid and reason are already documented in the schema, so no value is lost.

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 description opens with a specific verb+resource: type text into a running guest's console and/or press keys. It enumerates the exact key vocabulary, which makes it trivially distinguishable from console_click and console_type_password. An agent can tell what this tool does 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 Guidelines4/5

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

It clearly explains the internal decision between the text+keys shorthand and the steps array, including the ordering rule and a concrete example. It falls short of a 5 because it gives no explicit exclusions or pointers away from siblings such as console_type_password or console_click, leaving the agent to infer that passwords should go elsewhere.

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