Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

get_screenshot

Capture Connect IQ simulator screenshots in screen, bezel, or annotated debug views; crop, mask, OCR, and save images to verify watch app UI and layout.

Instructions

Capture a screenshot of the Connect IQ simulator. Supports watch display crop ('screen', 1:1 pixel mapping), full window with bezel ('bezel'), or annotated debug view with button hitboxes and coordinate grid ('annotated').

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": "get_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
maskNoMask the screen view to a circle (round devices)
viewNoScreenshot view mode: 'screen' crops to watch display; 'bezel' captures device bezel; 'annotated' composites SVG debug overlay (default: 'screen')
formatNoOutput format (default: png)
regionNoCrop region in processed screenshot pixels
device_idNoDevice profile ID (defaults to active device)
hash_onlyNoReturn the hash and metadata without the image payload
save_pathNoOptional file path on disk to save the image
inline_ocrNoRun OCR on the captured image and include the text
expect_textNoFail with E_TEXT_NOT_FOUND unless the OCR text contains this value

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden. It does add real behavioral context about what each view mode composites (bezel, SVG debug overlay, coordinate grid), which goes beyond the parameter list. It omits side effects such as save_path writing to disk, the E_TEXT_NOT_FOUND failure behavior of expect_text, and any prerequisite about an active simulator session.

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?

Two tight sentences with the core action front-loaded and the mode enumeration following immediately; there is no filler. It is efficient, though the mode list slightly duplicates what the schema's enum description already states.

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 nine-parameter capture tool with no annotations and no output schema, the description covers the primary output-shape decision (which view) but leaves return behavior, error semantics, and disk-write side effects undocumented. The 100% schema coverage compensates for most parameter-level gaps, making this adequate but not complete.

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 the schema already documents all nine parameters including enum meanings, defaults, and the nested region object. The description reinforces the 'view' enum with slightly richer wording ('1:1 pixel mapping', 'button hitboxes and coordinate grid') but adds no syntax or interaction detail for mask, region, hash_only, inline_ocr, or expect_text. Baseline 3 applies when the schema does the heavy lifting.

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 gives a specific verb and resource ('Capture a screenshot of the Connect IQ simulator') and immediately enumerates the three capture modes, so an agent knows exactly what the tool produces. It stops short of naming which sibling it is not (e.g. diff_screenshot, capture_window), so it lands at 4 rather than 5.

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 three view modes imply when each is useful ('annotated' for debugging button hitboxes and coordinates, 'screen' for 1:1 pixels), which is genuine implied usage guidance. However, there is no explicit when-to-use vs when-not, no mention of diff_screenshot or recognize_image_text as alternatives, and no stated prerequisite such as the simulator needing to be running.

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