Skip to main content
Glama

click

Presses a button or control from the last read window by handle and reference, enabling an AI agent to perform Windows UI actions.

Instructions

Press a button or other control from the last read_window.

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": {
      "handle": "<handle>",
      "ref": "<ref>"
    },
    "name": "click"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYes
handleYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

With zero annotations the description carries the full burden, and it discloses only the stale-state dependency on the last read_window. It says nothing about whether the click is synthetic or native, permission or focus requirements, failure behavior when the ref is stale or the control is disabled, or whether the action is reversible.

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 short, front-loaded sentence with no filler. It is efficient, though the single sentence also carries no structure to separate action, prerequisite, and parameter meaning.

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

Completeness3/5

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

The output schema exists, so return values needn't be explained, and the window-state prerequisite is captured. However, for a stateful action tool with no annotations and 0% parameter coverage, the definition leaves key gaps around parameter meaning and failure modes.

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 0%, so both required parameters (handle, ref) are undocumented in the schema; the description only vaguely gestures at them via "control from the last read_window." It implies ref identifies a control within a previously read window, but the handle/ref relationship and format are never explained.

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 specific verb ("Press") plus a specific resource ("a button or other control"), which is clearly an action tool distinct from read_window/list_windows. The only shortfall is that it never distinguishes itself from set_text, though the verb itself does most of that work.

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?

"from the last read_window" encodes a real prerequisite: the target must come from the most recent window read, implying read_window must be called first. There is no explicit when-not guidance, no mention of what to do if no window has been read, and no stated alternative route.

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

Deploy Server

Other Tools