Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

inspect_ui

Read the simulator's Accessibility hierarchy, including menus and native dialogs, to locate UI elements before acting; pass a window handle to target a specific dialog.

Instructions

Read simulator Accessibility hierarchy, including menus and native dialogs. Pass hwnd to inspect a dialog from list_windows. Paths are ephemeral: inspect before acting.

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": "inspect_ui"
  }
}

Input Schema

NameRequiredDescriptionDefault
hwndNoWindow handle from list_windows; omit for the main simulator window
depthNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it delivers the single most important behavioral fact: element paths are ephemeral, so a stale inspection cannot be reused for a later action. It also discloses that the tree spans menus and native dialogs, not just the app surface. It omits failure modes, cost/size of the hierarchy, and the requirement that a simulator be running.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with no waste: the core capability comes first, the parameter routing second, and the critical caveat last. Every sentence carries distinct information.

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, non-destructive read with no output schema, the definition covers what the tool returns conceptually and how to target a dialog. The one real gap is the undocumented depth parameter, which an agent may need to tune for large hierarchies.

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 50%: hwnd is already documented in the schema as coming from list_windows with omission meaning the main window, and the description largely restates that. The depth parameter has no description anywhere, and the description does not explain what it controls or why the default of 7 matters.

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: 'Read simulator Accessibility hierarchy,' and narrows scope with 'including menus and native dialogs,' which distinguishes it from screenshot/text-recognition siblings that return pixels rather than a structured tree. It does not explicitly contrast itself with those siblings, keeping it just below a 5.

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 concrete routing: pass hwnd to inspect a dialog obtained from list_windows, and 'inspect before acting' implies the read-then-act sequence with act_on_ui. It stops short of stating when to prefer this over get_screenshot or recognize_image_text, so it is clear context without explicit exclusions.

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