Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

swipe_screen

Simulates a touch drag gesture on the watch display in a cardinal direction, respecting device gesture thresholds, to navigate pages or test gesture-driven UI.

Instructions

Synthesize a touch drag gesture on the watch display in a cardinal direction ('up', 'down', 'left', 'right'), adhering to device gesture thresholds.

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": {
      "direction": "<direction>"
    },
    "name": "swipe_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
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 swipe before capturing screenshot (default: 350)
device_idNoDevice profile ID (defaults to active device)
directionYesDirection of swipe gesture: 'up' (next page), 'down' (previous page), 'right' (back/exit), 'left'
settle_msNoMilliseconds to wait before the after-capture used for the receipt (default: 400)
capture_afterNoWhether to capture a screenshot after swiping (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. 'Synthesize' usefully signals injected/synthetic input, and 'adhering to device gesture thresholds' hints that undersized drags may not register, but failure modes, permission requirements, and whether it blocks until the gesture completes are left unstated.

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 front-loaded sentence that names the core action first and the constraint second, with no filler or redundancy.

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?

The parameters are fully specified by the schema, but with no annotations and no output schema the description should explain what the call produces (the after-screenshot 'receipt' implied by settle_ms/capture_after) and what happens on assertion failure. Adequate but leaves meaningful gaps for an agent deciding how to chain this tool.

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%, so all six parameters are already documented with enums and defaults. The description only restates the direction enumeration that the schema already defines, adding no meaning about timing, capture, or assertion behavior beyond it.

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 ('synthesize a touch drag gesture on the watch display') plus the constrained input domain (cardinal directions). This is clearly distinguishable from tap_screen and hold_screen by the gesture type, though it never names those siblings explicitly.

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?

There is no when-to-use or when-not-to-use guidance. Nothing tells the agent to prefer this over tap_screen, press_button, or press_button_sequence, nor what preconditions must hold (e.g., an app in foreground). The only navigation hints ('next page', 'back/exit') live in the schema, not the description.

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