Skip to main content
Glama

desktop_click

Destructive

Click on a desktop session at a point of the last screenshot. The user started this desktop session for you in Termalin and can watch it. Coordinates are pixels of your last desktop_screenshot. Never type passwords, keys or other secrets: when a sign-in or secret is needed, stop and ask the user to type it themselves.

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": {
      "session_id": "<session_id>",
      "x": "<x>",
      "y": "<y>"
    },
    "name": "desktop_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesHorizontal position, in pixels of the last desktop_screenshot
yYesVertical position, in pixels of the last desktop_screenshot
buttonNoDefault left
doubleNoDouble-click
session_idYesDesktop session id from desktop_list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructive=true, openWorld=true, idempotent=false, so the mutating nature is covered structurally. The description adds real context the annotations cannot: the session is user-visible and watchable, clicks land in the screenshot coordinate space, and the agent must halt and hand off secret entry. It still does not say what happens after a click (whether state changes are observable only via a fresh screenshot) or how clicks behave if the screen has changed since the last capture.

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 compact sentences, front-loaded with the action and coordinate frame before the safety warning. No filler, though the secret-handling sentence is arguably a policy statement that could sit in a shared preamble.

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, the description still covers the input reference frame, the session origin and a hard safety rule, which is close to sufficient for a five-parameter click tool. The main remaining gap is that an agent cannot infer from the text that verification requires a follow-up desktop_screenshot.

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?

Schema coverage is 100%, so x, y, button, double and session_id are all documented in the schema itself. The description only restates the x/y reference frame and adds nothing about button or double, so it does not exceed the schema-implied baseline.

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?

States a specific verb (click) and resource (desktop session) plus the coordinate reference frame, which clearly separates it from desktop_move, desktop_scroll and desktop_key. It stops short of naming an alternative tool or explicitly contrasting behavior with its siblings.

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?

Gives a clear precondition (coordinates are relative to the last desktop_screenshot, session comes from desktop_list) and an explicit stop condition for sign-ins and secrets. It does not say when an agent should prefer desktop_move or desktop_key over repeated clicks, so routing guidance is implicit rather than spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.