Skip to main content
Glama

desktop_click

Clicks a named control in a native Windows window via UI Automation's Invoke pattern, avoiding blind coordinate clicks and accidental actions.

Instructions

Click a control in a native Windows window, by its visible name.

Uses UI Automation's Invoke pattern - not blind coordinates - so nothing is clicked by accident. Needs the desktop_control permission (default: ask).

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": {
      "title": "<title>",
      "control": "<control>"
    },
    "name": "desktop_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
controlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden. It does add genuine behavior beyond the schema: the Invoke pattern, a safety claim that nothing is clicked by accident, and the desktop_control permission with its default 'ask' prompt. It omits failure behavior when a control is not found or names are ambiguous, whether it waits for the UI, and what a call returns.

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 short sentences, front-loaded with the action and target before mechanism and permissions. Every sentence carries information, though the reassurance clause 'so nothing is clicked by accident' restates the coordinate contrast already made.

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?

For a two-parameter, no-output-schema tool with a permission prompt, the definition covers mechanism, platform scope, and authorization. The remaining gap is outcome semantics (success/failure, ambiguity handling), which matters for an agent driving a GUI but is a narrower omission than in a fully opaque tool.

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 0%, so the description must compensate for two bare parameters named title and control. It clarifies that control is the control's visible name and implies title identifies the target window, which is useful but incomplete. It says nothing about whether matching is exact or substring, how to disambiguate duplicates, or the required title format.

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?

The definition states a specific verb ("Click") and resource ("a control in a native Windows window") and pins down the mechanism, UI Automation's Invoke pattern rather than coordinates. This implicitly separates it from the coordinate-based sibling hands_click, though it never names that sibling. The scope (native Windows only) is a real differentiator an agent can act on.

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?

The invocation condition is implied: use this when you know a control's visible name inside a native Windows window, and prefer it over blind-coordinate clicking. There is no explicit statement of when NOT to use it, no mention of what to do if the control name is unknown, and no named alternative such as desktop_inspect for discovering names or hands_click for pixel targets.

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