Skip to main content
Glama
Garmin Simulator MCP
by dqclqn

build_app

Compile a Monkey C project with the SDK monkeyc compiler for a target Garmin device, producing a .prg binary for simulator testing or release builds.

Instructions

Build a Monkey C project for a specified device using the SDK monkeyc compiler.

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": "build_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
device_idNoGarmin device ID to build for (e.g. 'fenix847mm'). Defaults to active device.
extra_argsNoExtra CLI flags to pass directly to monkeyc
timeout_msNoHard build deadline; monkeyc is killed with E_TIMEOUT
jungle_fileNoPath to jungle build file (defaults to project_dir/monkey.jungle)
project_dirYesPath to Monkey C project directory containing monkey.jungle or manifest.xml
debug_channelNoSwap in the debug automation config before building (default: true). Set false for a release build with the channel disabled.
output_prg_pathNoDestination file path for output .prg binary
developer_key_pathNoPath to developer key (.der). Defaults to developer_key.der in project or SDK.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
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 burden of behavioral disclosure. It mentions invoking the monkeyc compiler but omits key effects such as writing or overwriting a .prg file, developer-key requirements, timeout/error behavior, and debug-channel implications.

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?

The definition is a single front-loaded sentence with no filler. Each phrase contributes to the core action, compiler, and device scope.

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

Completeness2/5

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

This is a complex build tool with no annotations and no output schema. The description is too sparse: it does not explain build prerequisites, generated output behavior, failure modes, or safe usage context.

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 eight parameters. The description adds only that a device can be specified, which does not add meaning beyond the device_id schema description.

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 states a specific verb and resource: build a Monkey C project. It also identifies the device scope and compiler used. It stops short of distinguishing itself from close siblings such as run_app or run_unit_tests.

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 guidance on when to use this tool versus run_app, run_unit_tests, or other build/debug siblings. No prerequisites, exclusions, or workflow context are given.

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