Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

console_screenshot

Captures a running Proxmox guest's console screen; use an optional region to return native-pixel detail for reading small text.

Instructions

A picture of a running guest's screen — wider screens are shrunk by a whole factor (1920×1080 comes as 960×540). To read small text, give region: that part of the picture comes back at the screen's own pixels. console_click always takes x, y of the whole picture.

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_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesThe host's id, from list_hosts.
vmidYesThe guest's ID (VMID).
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.
regionNo[x0, y0, x1, y1] in the whole picture's numbers (as console_click's x, y): its top-left and bottom-right corners.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false), so the description is where the real behavioral detail lives, and it delivers: downscaling by a whole factor, the exact dimension example, and the fact that region output returns at native screen pixels. The only gap is that it never says the image is delivered as an image payload or whether anything about the guest state changes, despite readOnlyHint being false.

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?

Three tight sentences, front-loaded with the core behavior and the scaling caveat before the region tip. The closing sentence about console_click coordinates is terse to the point of being slightly oblique on first read, but no sentence 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?

With no output schema and four parameters, the description covers the two things an agent would otherwise get wrong: the downscaled resolution and the coordinate frame for region versus console_click. What is missing is the delivery format of the image and any note on multi-monitor or guest-not-running behavior.

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 100%, so 3 is the baseline, but the description adds meaning the schema cannot: it explains the coordinate frame for region (whole-picture numbers, matching console_click's x/y) and the quality tradeoff that motivates passing it. The host/vmid/reason parameters are left entirely to the schema, which is acceptable given full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"A picture of a running guest's screen" states the resource and the action concretely, and the scaling example (1920×1080 → 960×540) pins down what a caller actually receives. It stops short of naming when to prefer console_record or another capture sibling, so the purpose is clear but sibling differentiation is only indirect via the console_click coordinate note.

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?

"To read small text, give region" is a genuine conditional usage hint tied to a real workflow, and the closing sentence warns that click coordinates are in whole-picture space. However, there is no statement of when to use this instead of console_record or other capture/observation siblings, and no exclusions or prerequisites beyond the implicit requirement that the guest be running.

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