Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

trigger_menu_action

Clicks macOS ConnectIQ.app menu items via Accessibility to change simulation data or activity settings, optionally capturing a screenshot afterward.

Instructions

Trigger a macOS menu item in ConnectIQ.app via Accessibility (AXUIElement), such as simulation data or activity settings.

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": {
      "menu_path": "<menu_path>"
    },
    "name": "trigger_menu_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
wait_msNoMilliseconds to wait after menu click before capturing screenshot (default: 400)
menu_pathYesHierarchical menu path to click, e.g. ['Simulation', 'Activity Data'] or ['Settings', 'Glance View']
capture_afterNoWhether to capture a screenshot after menu trigger (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden. Naming AXUIElement implies macOS Accessibility permission is involved, which is useful, but the description does not state that ConnectIQ.app must already be running, that the menu path must exist, what happens on a bad path, or that a screenshot is captured as a side effect (that only appears in the schema). For a UI-mutating tool this leaves significant behavioral gaps.

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?

A single front-loaded sentence with no filler; the action, target app, mechanism, and example scope are all in the first clause. Only the trailing 'such as' examples delay the point slightly.

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?

There is no output schema and no annotations, so the description must carry prerequisites and failure behavior. It omits that the app must be running, that Accessibility permissions are required, and that the tool returns/captures a screenshot, leaving an agent without what it needs to call this reliably in a failure case.

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 all three parameters, including menu_path examples and default values for wait_ms and capture_after, are already documented. The description adds no syntax or format detail beyond what the schema provides, so this sits at the baseline.

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 description states a concrete verb and resource: trigger a macOS menu item in ConnectIQ.app, and names the mechanism (Accessibility/AXUIElement). It also gives concrete menu examples like simulation data and activity settings. It does not distinguish this from siblings such as act_on_ui or press_button, so it stops short of 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 Guidelines2/5

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

The examples hint at what kinds of menus exist, but there is no when-to-use versus when-not guidance and no mention of alternatives such as act_on_ui, press_button, or inspect_ui. An agent must infer whether a menu item or a UI element press is the right call.

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