Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

console_click

Clicks, double-clicks, right-clicks, or scrolls at x,y on a running VM's current console screenshot to control installers and desktops that need mouse input.

Instructions

Click — or double-click, right-click, or turn the wheel (scroll: + up, − down) — on a running guest's screen at x, y of the latest console_screenshot picture (take a fresh one first: the click lands where things are now). For installers and desktops that need the mouse; keys (console_send) are surer where they work. The user sees a red mark where it will land. It needs an absolute pointer in the VM (a USB tablet; Linux also has QEMU's vmmouse): without one it says so and clicks nothing.

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>",
      "x": "<x>",
      "y": "<y>",
      "reason": "<reason>"
    },
    "name": "console_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYes
yYes
hostYesThe host's id, from list_hosts.
vmidYesThe guest's ID (VMID).
buttonNo
doubleNo
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.
scrollNoWheel steps instead of a click.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false) by disclosing a hardware prerequisite, the graceful-failure behavior ("it says so and clicks nothing"), the visual side effect ("the user sees a red mark where it will land"), and the coordinate-frame dependency on screenshot freshness. None of that is inferable from the schema or annotations.

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 the core action and no filler sentences, but the first sentence is heavily nested with em dashes and parentheses, which makes it denser to parse than necessary. Every sentence still earns its place.

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?

For an 8-parameter, non-idempotent UI-driving tool with no output schema, the description covers purpose, prerequisite, failure mode, user-visible effect, and coordinate semantics. Nothing an agent needs in order to call it correctly is missing.

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 only 50%, but the description compensates for the undocumented parameters: button values (left/middle/right-click), double, scroll magnitude and sign (+ up, − down), and the coordinate frame for x/y. It stops short of saying whether x/y are pixels from a specific origin or how scroll combines with x/y as a wheel position, so a small gap remains.

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 (click/double-click/right-click/wheel) and an exact resource (a running guest's screen at x, y of the latest console_screenshot picture). It also draws the boundary against the sibling console_send ("keys are surer where they work"), so an agent can pick between them 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 usage conditions and prerequisites: take a fresh screenshot first, prefer keys where they work, and only use this for installers/desktops that need the mouse. It even states the failure condition (needs an absolute pointer such as a USB tablet or vmmouse) that selects against using it at all.

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