Skip to main content
Glama

desktop_mouse_click

Clicks at absolute screen coordinates to interact with desktop UI elements, supporting button choice, click count, and held modifier keys.

Instructions

agent-desktop mouse-click: Click at absolute screen coordinates (requires --headed)

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": {
      "xy": "<xy>"
    },
    "name": "desktop_mouse_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
xyYesAbsolute coordinates as x,y; requires --headed; write a negative value with = (--xy=-100,50)
countNoNumber of clicks
buttonNoMouse button: left, right, middleleft
modifiersNoHeld modifiers: shift, meta, ctrl, alt (repeatable; cmd is accepted)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.6/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of disclosure. It does add a genuine prerequisite (--headed), but it says nothing about whether the cursor moves, whether the click is blocking, what happens if the coordinates are outside the viewport, or whether the target window must be focused first. For a synthetic input/mutation tool, that leaves a large 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?

One sentence, front-loaded with the action, with the prerequisite in parentheses. The 'agent-desktop mouse-click:' prefix duplicates the tool name and could be dropped, but overall the text is tight.

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

Completeness2/5

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

For a tool that has four parameters, no annotations, and no output schema, the definition should explain the click's effects and how it relates to the many sibling click tools. As written, it only covers the action and one prerequisite, so the agent still lacks enough context about the effects of this call to use it confidently.

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 description coverage is 100%, so xy, count, button, and modifiers are already documented, including the negative-coordinate '=' syntax. The description only echoes the --headed constraint already present in the xy schema entry, adding little meaning beyond the structured data.

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

Purpose3/5

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

The description states a concrete verb and resource: "Click at absolute screen coordinates." That is more than a restatement of the name, but the context includes many click-like siblings (desktop_click, desktop_double_click, desktop_right_click, desktop_mouse_down). The definition never explains how this absolute-coordinate click differs from them, so an agent still has to guess.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

The only guidance is a runtime prerequisite, "(requires --headed)," which tells the agent the tool is unavailable in headless mode. The description gives no guidance on when to choose this tool over desktop_click or desktop_hover, and no guidance on when not to use it.

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