Skip to main content
Glama

create_workout

Create a new structured workout in the user's Garmin workout library. It never edits an existing one. A workout reaches the watch once it is scheduled on a date.

Args: name: Shown in Garmin Connect and on the watch. steps: Ordered steps, each with "type" (warmup, interval, recovery, rest, cooldown or repeat) and exactly one of "duration_seconds", "distance_meters" or "until_lap": true (the step ends on the lap button). A repeat is {"type": "repeat", "times": 5, "steps": [...]} and can't contain another repeat. Optional target on a step: "pace" (min/km, "4:05" or ["4:00", "4:10"]), "hr" (bpm [150, 165], or a Garmin zone such as "z2" or "z3-z4") or "power" (watts, 250 or [240, 260]; a share of the FTP set in Garmin, "95%" or ["88%", "94%"]; or a power zone, "z3"). A pace target narrower than 5 s/km either side is widened to that, and a single power value becomes a range 5% either side. Example, 15 min warm-up, 5 x 1 km at 4:05 with 90 s recoveries, 10 min cool-down: [{"type": "warmup", "duration_seconds": 900}, {"type": "repeat", "times": 5, "steps": [{"type": "interval", "distance_meters": 1000, "pace": "4:05"}, {"type": "recovery", "duration_seconds": 90}]}, {"type": "cooldown", "duration_seconds": 600}] sport: running (default), cycling, swimming, walking or hiking. description: Optional note stored with the workout. pool_length_meters: For a swim, 25 (default) or 50.

A swim's steps are whole pool lengths (100, 200...), each with an optional "stroke": freestyle, backstroke, breaststroke, butterfly, im, drill or any. Its "pace" is per 100 m ("1:45") and shows on the step as a note rather than an alert. A "rest" with no duration waits for the lap button; "duration_seconds" fixes its length. A "note" (e.g. "kick with board") shows on the step.

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": {
      "name": "<name>",
      "steps": "<steps>"
    },
    "name": "create_workout"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNo
nameYes
sportNorunning
stepsYes
descriptionNo
pool_length_metersNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / date
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare it is a non-destructive, non-open-world write; the description adds substantial behavior beyond that: pace targets narrower than 5 s/km are widened, a single power value becomes a ±5% range, repeats cannot nest, swim steps must be whole pool lengths, and a swim pace target renders as a note rather than an alert. These are exactly the silent normalizations an agent needs to know 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Long, but the length is driven by a genuinely complex nested payload; the purpose sentence is front-loaded, the Args section is scannable, and the concrete 5x1km example compresses a lot of specification into one line. A few rest/note details repeat the until_lap rule, but nothing is wasted.

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?

An output schema exists, so return values need no explanation, and the description covers the mutation's side effects and the full step grammar. The only material omission is `date`, whose presence in the schema is unexplained — the agent must infer that passing it schedules the workout.

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 description coverage is 0%, so the description must carry all six parameters, and it does an unusually good job on the hardest one — the nested steps grammar (type, duration/distance/until_lap exclusivity, repeat shape, target formats) with a worked example. The gap is the `date` parameter, which is never listed in Args and only obliquely referenced by the scheduling sentence.

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 ("Create a new structured workout in the user's Garmin workout library") and immediately scopes it against the edit case ("It never edits an existing one"), which separates it from update_workout. The sport argument further distinguishes it from create_strength_workout.

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?

"A workout reaches the watch once it is scheduled on a date" tells the agent that creation alone does not put the workout on the device, implying the scheduling step. It does not name schedule_workout explicitly nor state exclusions beyond the no-edit note, so guidance is clear but not fully routed.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources