garmin-connect-api

Push workout to device

push_workout_to_device

Queue a saved workout to a Garmin watch so it installs at the device's next sync; optionally choose a device ID or let the account default be selected.

Instructions

Queue a saved workout for one of the account's watches; it arrives at the watch's next sync, not immediately.

Without device_id it goes to the device last used, if it is on the account's list, else the primary activity tracker, else the only device; when none of those settles it, the call is refused and asks for a device_id. list_devices gives the ids, and the reply names the device chosen. Pushing does not schedule it: to put it on a date, use schedule_workout.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`device_id`	No	From list_devices. Left out, chosen as described.
`workout_id`	Yes	From list_workouts or list_scheduled_workouts.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 20, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations already cover the safety profile (non-readOnly, non-idempotent, openWorld, non-destructive), and the description goes well beyond them: async queued delivery at next sync, deterministic device fallback logic, refusal behavior when resolution fails, and that the reply names the chosen device. No contradiction with annotations.

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?

Front-loaded with the core behavior, then the optional-parameter resolution, then the disambiguation from schedule_workout. Dense but every sentence adds actionable information with no filler.

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 mutation with an output schema present, the description covers everything the agent needs: delivery timing, id sourcing, fallback resolution, refusal behavior, and the sibling alternative. Nothing material is missing, and return values are rightly left to the output schema.

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 coverage is 100%, so the baseline would be 3, but the description adds real meaning beyond the schema by spelling out the multi-step fallback used when device_id is omitted and reaffirming that list_devices supplies valid ids. This is exactly the kind of semantic detail the schema cannot express.

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?

States a specific verb and resource ('Queue a saved workout for one of the account's watches') and immediately clarifies the delivery model ('arrives at the watch's next sync, not immediately'). It also distinguishes itself from sibling schedule_workout, so an agent can tell the two apart without opening schemas.

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?

Gives an explicit routing rule to a sibling: 'Pushing does not schedule it: to put it on a date, use schedule_workout.' It also documents the full default-device resolution chain and the failure case ('refused and asks for a device_id'), leaving no ambiguity about when this tool is appropriate.

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