Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

matrix_run

Build and run a Connect IQ app on multiple devices, capture screens, optionally execute button/touch scenarios, and compare each step with .ciq baselines, creating or updating them when needed.

Instructions

Build, run and capture one screen per device, optionally run a button/touch scenario, and compare each step against .ciq/baselines. Creates baselines when missing or when update_baselines is true.

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": {
      "project_dir": "<project_dir>",
      "devices": "<devices>"
    },
    "name": "matrix_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsNoOptional input scenario run after the first capture, with a baseline per step
devicesYesDevice ids from list_devices
wait_msNoMonkeydo startup wait per device (default: 3000)
isolatedNoLaunch on a hidden desktop when the simulator is not running (default: true on Windows)
settle_msNoExtra settle time before capture (default: 1200)
thresholdNoPer-pixel channel delta for diffs (default: 12)
output_dirNoCurrent capture directory (default: <project>/.ciq/current)
jungle_fileNoExplicit jungle file
project_dirYesMonkey C project directory
baseline_dirNoBaseline directory (default: <project>/.ciq/baselines)
debug_channelNoBuild with the debug automation channel (default: true)
update_baselinesNoOverwrite baselines with this run
reset_before_eachNoClear app storage and stop the app before each device (default: true)
developer_key_pathNoExplicit developer key

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?

No annotations are supplied, so the description carries the full burden. It does disclose a meaningful side effect — baselines are created when missing or when update_baselines is true — and that a build plus per-device launch occurs. However, it omits the cost profile (build + simulator startup per device, wait_ms/settle_ms timing), the filesystem writes to baseline_dir and output_dir, and any note about developer key or isolated-desktop requirements.

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 compact sentences, front-loaded with the primary action sequence and followed by the baseline-comparison behavior. Every clause carries information; there is no filler or restatement of the tool name.

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 14-parameter, build-and-compare tool with no annotations and no output schema, the description should say what the agent gets back (per-device/per-step pass or diff results) and what happens on mismatch. It explains the baseline lifecycle but leaves the return shape and failure behavior unspecified, which is a real gap given the tool's complexity.

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 14 parameters including defaults are already documented in the schema. The description adds only that the steps scenario is optional and that update_baselines overrides existing baselines; it adds no extra meaning about device selection, threshold semantics, or baseline_dir layout. Baseline 3 is appropriate 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 uses specific verbs and resources: build, run, capture one screen per device, optionally execute a button/touch scenario, and compare each step against .ciq/baselines. That is far more concrete than the bare name 'matrix_run'. It stops short of explicitly naming a sibling (e.g. matrix_diff or run_app) as the alternative, so the agent must infer the boundary.

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 rather than stated: 'one screen per device' and 'compare each step against baselines' suggest a multi-device visual regression workflow. There is no explicit when-to-use vs run_app, matrix_diff, or capture_window guidance, and no prerequisites such as needing a running simulator or the device ids coming from list_devices (that hint lives only in the schema).

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