Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

hold_screen

Simulate a long-press at specified watch touchscreen coordinates to open watchface complications or menus, then capture the resulting screen.

Instructions

Long-press at specific coordinates on the watch touchscreen (e.g. to open a watchface complication or menu).

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": {
      "x": "<x>",
      "y": "<y>"
    },
    "name": "hold_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesX coordinate: display pixels or normalized ratio
yYesY coordinate: display pixels or normalized ratio
expectNoAssert the outcome: 'change' fails with E_NO_CHANGE when the screen is identical, 'noop' fails with E_UNEXPECTED_CHANGE when it differs
wait_msNoMilliseconds to wait after touch before capturing screenshot (default: 350)
device_idNoDevice profile ID (defaults to active device)
settle_msNoMilliseconds to wait before the after-capture used for the receipt (default: 400)
normalizedNoWhether coordinates are normalized 0.0 to 1.0 (default: false)
duration_msNoTouch hold duration in milliseconds (default: 1000)
capture_afterNoWhether to capture a screenshot after holding (default: true)

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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing beyond the gesture itself. It never mentions that a screenshot is captured by default after the hold (capture_after), that an assertion mode can fail the call (expect), or that the action may change device UI state.

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?

One sentence, front-loaded with the verb and target, with the example appended as useful context rather than filler. Nothing is wasted or restated from the schema.

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?

For a 9-parameter device-interaction tool with no annotations and no output schema, the definition is thin: it says nothing about the screenshot receipt the tool produces, the failure modes implied by expect, or how this differs from other touch tools. The rich input schema covers parameters, but the behavioral and return-side context is absent.

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 100%, with every parameter documented including defaults and the enum assertion semantics, so the baseline of 3 applies. The description adds only that the coordinates target a hold point, giving no extra meaning to duration_ms, settle_ms, or expect beyond the schema.

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 (long-press) and resource (touchscreen coordinates on the watch), plus a concrete example use case (watchface complication or menu). The verb itself distinguishes it from tap_screen/swipe_screen, though no sibling is named 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?

The parenthetical example implies when to reach for a long-press rather than a tap, but there is no explicit guidance on when not to use it, nor any named alternative for a single short touch or drag. Usage is inferable rather than stated.

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