Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

dev_loop

Build and run a Connect IQ project in the local simulator, capture the first stable frame, and return recent log lines in one call.

Instructions

Build the project, run it, capture the first stable frame and return the latest log lines in one call.

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>"
    },
    "name": "dev_loop"
  }
}

Input Schema

NameRequiredDescriptionDefault
wait_msNoMonkeydo startup wait (default: 2500)
device_idNoDevice id (defaults to active device)
log_linesNoLog lines to return (default: 40)
settle_msNoReserved settle time for future frame selection
jungle_fileNoExplicit jungle file
project_dirYesMonkey C project directory
debug_channelNoBuild with the debug automation channel (default: true)
developer_key_pathNoExplicit developer key

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the significant side effect that this builds and launches the app on a device. It does not cover failure behavior (what happens if the build fails), blocking duration (default wait_ms of 2500 plus settle time), or whether the app is left running after the call.

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 enumerates the steps in execution order and ends with the key differentiator 'in one call'. No filler or repetition.

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 composite tool with eight parameters and no output schema, the description should state what is returned. It says logs are returned but leaves ambiguous whether the captured frame is returned, saved to disk, or merely used internally, and it omits error/timeout semantics that matter for a multi-second orchestration call.

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 eight parameters are already documented in the schema, including defaults and the 'reserved for future' note on settle_ms. The description adds no parameter-level meaning beyond that, which is the expected baseline when the schema does the work.

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 names a concrete four-step composite action (build, run, capture first stable frame, return log lines) with the explicit qualifier 'in one call', which signals it bundles what siblings like build_app, run_app, get_screenshot, and get_app_logs do separately. It is specific about the resource and scope, though it never names those siblings directly.

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?

'In one call' implies the intended use case is replacing a manual build/run/capture/log sequence, so the usage is inferable. However, there is no explicit statement of when to prefer this over the individual tools, and no prerequisites (simulator must be launched, device must be active) or exclusions are given.

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