Skip to main content
Glama

desktop_inspect

Inspect a native Windows window to read its UI control tree via Windows UI Automation, listing each control's name, type, position, and state so agents can understand the window before acting.

Instructions

Look inside a native Windows window: its controls (name, type, position, state).

This is the desktop equivalent of eyes_see_browser - it reads the real UI tree through Windows UI Automation, so controls are found by their visible name. Reading is allowed; acting on the window needs the desktop_control permission.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "desktop_inspect"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden. It usefully discloses the underlying mechanism (Windows UI Automation), the lookup model (controls matched by visible name), and the permission boundary between reading and acting, but says nothing about what happens for a missing/ambiguous window or about the cost/latency of a tree traversal.

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 tight sentences with the core action front-loaded and the permission caveat trailing, which is the right ordering. Minor redundancy in the em-dash gloss, but nothing that wastes an agent's attention.

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?

For a one-parameter, no-annotation, no-output-schema read tool this covers mechanism, output shape, and permission boundary reasonably well. It still leaves the caller guessing about the empty-title default and about behavior when no matching window exists, which are the two things most likely to cause a failed call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'title' has 0% schema description coverage and is never mentioned in the description, so the agent must infer that it names the target window. The default empty string is especially opaque — it is unclear whether that means the foreground window, the last-focused window, or an error.

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-and-resource pair: reads the control tree (name, type, position, state) of a native Windows window via Windows UI Automation. The eyes_see_browser analogy anchors it as a read-only inspection tool, though it does not explicitly differentiate itself from the sibling eyes_see_desktop.

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?

Implies the use case (finding controls by visible name before acting on them) and notes that reading is permitted while acting requires the desktop_control permission. It gives no explicit when-not guidance or named alternative for cases where a window cannot be found or when a different inspection tool is more appropriate.

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