Skip to main content
Glama
Connect IQ MCP

Connect IQ MCP

by idoo

Build with monkeyc

sdk_build

Builds Garmin Connect IQ projects: compile a single-device PRG or a device "all" store .iq package, with structured diagnostics and build_id polling for long runs.

Instructions

monkeyc build: one device PRG, or device "all" for the store .iq (never replaces an .iq without overwrite). Key defaults to CIQ_MCP_KEY. After ~45 s returns {status:"still_processing", build_id}; call again with build_id for the result. Structured diagnostics.

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": "sdk_build"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNodeveloper key (.der) inside the root (default: CIQ_MCP_KEY, set by the human, may be outside the root)
sdkNoinstalled SDK version or dir name, e.g. 9.2.0 (default: CIQ_MCP_SDK env, current-sdk.cfg, newest installed); a custom SDK outside the SDK Manager dir only via CIQ_MCP_SDK
testNounit-test build (-t) of one device; not with release
deviceNodevice id, e.g. fenix7 (writes <project>/bin/<device>.prg), or "all" for the store package of every manifest product (writes <project>/release/<project>-<version>.iq; slow)
jungleNojungle file relative to the project (default monkey.jungle)
projectNoproject dir inside the root (default: root)
releaseNorelease build (-r); always on for device "all"
versionNodevice "all": version for the .iq name (default: manifest version, else a YYYYMMDD-HHMMSS timestamp)
build_idNowait for a build that returned still_processing; other args are ignored
overwriteNodevice "all": replace an existing .iq of the same name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, it discloses the destructive-boundary detail that the .iq is never replaced unless overwrite is set, plus the ~45 s timeout and still_processing/build_id continuation protocol that no annotation conveys. These are exactly the runtime traits an agent cannot infer from readOnlyHint/idempotentHint and would otherwise trip over. No conflict with the declared hints, since the default path is non-destructive.

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?

Dense and front-loaded: mode split first, then overwrite safety, then async polling, then return character. Every clause carries information, though the telegraphic phrasing ("one device PRG") costs a little readability without saving much space.

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 10-parameter, zero-required, side-effecting build tool with no output schema, the description covers the mode fork, the write targets, the safety boundary, and the async continuation. It stops short of covering failure behavior or what the diagnostics payload contains, but the model has enough to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description goes slightly further by naming the two output targets (bin/<device>.prg vs release/<version>.iq) that give device and version their meaning together. The remaining parameter details (key/sdk defaults, jungle, test exclusivity) are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"monkeyc build: one device PRG, or device \"all\" for the store .iq" states a specific verb and resource and immediately splits the two output modes, which is the key distinction an agent needs. Nothing in the sibling list (sdk_info, sdk_manifest_get, sim_run, etc.) overlaps with compiling, so the tool is unambiguous on its own.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

It gives clear operating context: device "all" is the slow store-package path, otherwise a single-device PRG, and overwriting an existing .iq requires the overwrite flag. The async contract (poll by build_id) is spelled out. It does not name exclusions or prerequisite ordering (e.g. key check before build), so it stops short of a 5.

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