Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

run_app

Push a compiled Monkey C .prg to the active Garmin simulator device, launch it with monkeydo, and stream logs for debugging.

Instructions

Push and run a compiled Monkey C executable (.prg) on the active device in the simulator using monkeydo, and stream logs.

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": {
      "prg_path": "<prg_path>"
    },
    "name": "run_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
wait_msNoMilliseconds to wait for app launch and initial log output (default: 2500)
prg_pathYesPath to the compiled executable .prg file
device_idNoGarmin device ID to run on (defaults to active device)
timeout_msNoHard startup deadline that kills monkeydo with E_TIMEOUT
capture_afterNoWhether to capture and return an initial watch screenshot after launching (default: true)
startup_timeout_msNoMaximum wait for a stable frame and startup log marker (default: 8000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose that logs are streamed and that monkeydo is the underlying mechanism, but it says nothing about side effects on the device (pushing files, replacing a running app), required simulator/device state, or failure modes — several of those details live only inside parameter descriptions.

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: action, target, mechanism, and output behavior in order of importance, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter launch tool with no annotations and no output schema, the description plus the rich schema fields cover what an agent needs to invoke it. The main remaining gap is that the returned payload (logs plus optional screenshot) is only implied by 'stream logs' and the capture_after parameter.

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 every parameter (wait_ms, startup_timeout_ms, timeout_ms, capture_after, device_id) is already documented in the schema. The description adds no parameter-level meaning beyond it, so the baseline 3 applies.

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 compound action — push and run a compiled .prg on the active simulator device via monkeydo — plus the side effect of streaming logs. That is enough to distinguish it from build_app and run_unit_tests, 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 Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"compiled ... executable (.prg)" implies the build step must already have run, which is an implicit precondition. There is no explicit when-to-use/when-not guidance and no mention of alternatives such as run_unit_tests or get_app_logs for retrieving logs after the fact.

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