Garmin Connect IQ Simulator MCP Server

Overview Schema Source Related Servers Discussions Admin

press_button

Simulate short or long presses on a Garmin device's physical bezel buttons, like select, back, up, or menu, to test app navigation and return the updated watch screen.

Instructions

Press a physical bezel button on the active Garmin device (e.g. 'select', 'back', 'up', 'down', 'menu'). Supports short clicks or long-press holds, and returns the updated watch screen.

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": {
      "button": "<button>"
    },
    "name": "press_button"
  }
}

Input Schema

Name	Required	Description
`hold`	No	Perform a long press (hold) instead of short click
`button`	Yes	Button identifier or alias (e.g. 'select', 'enter', 'start', 'back', 'esc', 'up', 'down', 'menu')
`method`	No	Input synthesis method: 'mouse' clicks bezel hitbox center; 'key' sends macOS virtual keycode (default: 'mouse')
`hold_ms`	No	Custom hold duration in milliseconds (defaults to 1200ms for hold, 80ms for short click)
`wait_ms`	No	Milliseconds to wait after button press before capturing screenshot (default: 350)
`device_id`	No	Device profile ID to resolve button coordinates from (defaults to active device)
`capture_after`	No	Whether to capture and return a screenshot after the button press (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 5, 2026

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 usefully discloses that a screenshot of the updated watch screen is returned (important since there is no output schema), but it says nothing about prerequisites such as an active/booted device, failure behavior if the bezel hitbox is unavailable, or side effects of navigation.

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?

A single well-ordered sentence: action, target, examples, supported modes, and return value. No filler, and the most decision-relevant information comes first.

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 7-parameter interaction tool with no annotations and no output schema, the description covers purpose and return shape adequately but omits device-state preconditions and error outcomes. Enough to invoke, not enough to invoke confidently in edge cases.

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 seven parameters are already documented in detail, including method, hold_ms, wait_ms, and capture_after defaults. The description adds only the conceptual short-click vs long-press framing, which the schema already covers via 'hold'. Baseline 3 applies.

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 ('press a physical bezel button') and names the target ('active Garmin device') with concrete button examples. It implicitly separates itself from send_key/tap_screen by specifying 'physical bezel button', though it never names a sibling explicitly.

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?

Usage is implied by the button examples and the short-click vs long-press distinction, but there is no guidance on when to choose this over send_key, tap_screen, hold_screen, or press_button_sequence. An agent must infer the boundary from the sibling names alone.

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