Skip to main content
Glama

push_workout_to_device

Queues a workout from your library to a Garmin device through Garmin Connect, so the watch receives it at its next sync. Specify the workout ID and optionally a device ID.

Instructions

Send a workout from the workout library to a Garmin device

    Queues the workout in Garmin Connect's device message queue, the same
    as "Send to Device" in the Garmin Connect app. The watch picks it up
    at its next sync with Garmin Connect (phone app or Wi-Fi), so it does
    not appear on the watch immediately. Scheduling a workout does not
    need this: scheduled workouts reach the watch's calendar on their own.

    Each call queues another copy, so do not push the same workout twice.

    Args:
        workout_id: ID of the workout to send (from get_workouts or upload_workout)
        device_id: Device ID (optional; defaults to the most recently used
            device; can be obtained from get_devices or get_device_last_used)
    

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": {
      "workout_id": "<workout_id>"
    },
    "name": "push_workout_to_device"
  }
}

Input Schema

NameRequiredDescriptionDefault
device_idNo
workout_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and the description reinforces the non-idempotent behavior with the concrete consequence: each call queues another duplicate copy. It adds behavior the annotations cannot express — asynchronous queue delivery, non-immediate appearance on the watch, and the next-sync pickup mechanism — which is exactly the context an agent needs before calling.

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?

Content is front-loaded with the purpose and the highest-risk caveat (not immediate) early; every sentence carries information. The docstring-style 'Args:' block and internal blank lines are slightly verbose formatting for an agent reading prose, but no sentence is wasted.

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

Completeness5/5

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

For a two-parameter async mutation with no output schema, the description covers the mechanism, timing, duplication hazard, cross-tool parameter sourcing, and the scheduling alternative. Nothing needed to invoke it correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does: workout_id's provenance is named (get_workouts or upload_workout) and device_id's optionality, default (most recently used device), and sourcing (get_devices or get_device_last_used) are spelled out. This fully compensates for the undocumented 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?

The first line gives a precise verb+resource pair (send a workout to a Garmin device) and the body immediately scopes it against the confusable alternative, schedule_workout, noting that scheduled workouts reach the watch calendar without this call. An agent can distinguish this from the create_*/schedule_* siblings without opening any schema.

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

Usage Guidelines5/5

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

The definition states when to use it (pushing a library workout to hardware), when not to (scheduling, which propagates on its own), and an explicit anti-pattern warning against calling twice for the same workout. The prerequisite context — the watch must sync via phone app or Wi-Fi — is also given, so timing expectations are set.

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

Deploy Server

Other Tools