Skip to main content
Glama

schedule_workout

Idempotent

Schedule a saved workout template on one calendar date. The workout appears on that date in the LiftTrack app and, when the user's Garmin account is linked, on their Garmin calendar and watch. If the workout is already on that date (scheduled once, by the weekly routine, or by a program), nothing is added and the existing entry is reported.

Args: workout_id: The workout's id, as a tool result lists it. Never show it to the user. workout_name: The workout's name, as that result lists it. A name that does not match the id is refused. date: YYYY-MM-DD, from today through 30 days ahead.

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>",
      "workout_name": "<workout_name>",
      "date": "<date>"
    },
    "name": "schedule_workout"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesCalendar date as YYYY-MM-DD
workout_idYesThe workout's workout_id, as a tool result lists it
workout_nameYesThe workout's current name, as its tool result lists it. Checked against workout_id; a mismatch is refused.

Output Schema

NameRequiredDescriptionDefault
dateYes
workout_idYes
workout_nameYes
existing_typeNo
garmin_linkedYes
already_scheduledYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • removedInput schema / properties / workout_folder_name
      Removed value: -{
      -  "description": "Folder that holds the workout, to disambiguate duplicate names. Use \"My Workouts\" for a workout not in any folder.",
      -  "type": "string"
      -}
    • addedInput schema / properties / workout_id
      Added value: +{
      +  "description": "The workout's workout_id, as a tool result lists it",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedInput schema / properties / workout_name / description
      Previous value: -"The exact name of the workout template"New value: +"The workout's current name, as its tool result lists it. Checked against workout_id; a mismatch is refused."
    • addedInput schema / properties / workout_name / minLength
      Added value: +1
    • changedInput schema / required
      Previous value: -[
      -  "workout_name",
      -  "date"
      -]New value: +[
      +  "workout_id",
      +  "workout_name",
      +  "date"
      +]
    • addedOutput schema / properties / workout_id
      Added value: +{
      +  "type": "string"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "workout_name",
      -  "date",
      -  "already_scheduled",
      -  "garmin_linked"
      -]New value: +[
      +  "workout_id",
      +  "workout_name",
      +  "date",
      +  "already_scheduled",
      +  "garmin_linked"
      +]
  2. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world. The description adds meaningful behavior beyond that: duplicates (scheduled once, by weekly routine, or by a program) result in no addition and the existing entry is reported, and an id/name mismatch is refused. It stops short of describing the response payload or failure modes beyond mismatch.

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?

Two behavioral sentences followed by a compact Args block; every clause carries operational information (effect, duplicate handling, validation, date bound). Front-loaded with the primary action and no filler.

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?

With an output schema present, return values need not be explained, and the description covers the external Garmin side effect, duplicate semantics, and parameter constraints. Only the error/refusal surface and the exact duplicate-report shape are left to the output schema, which is a minor gap for a three-required-parameter mutation.

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; the description earns above that by adding rules not in the schema — notably the date window (today through 30 days ahead) and the instruction never to show workout_id to the user. The id/name cross-check is largely restated from the schema.

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?

States a specific verb and resource plus scope: "Schedule a saved workout template on one calendar date." The phrase "saved workout template" distinguishes it from ad-hoc logging tools like schedule_run without naming a sibling, so differentiation is implied rather than explicit.

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

Usage Guidelines3/5

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

The definition supplies context about the effect (appears on the date in LiftTrack and on Garmin when linked) and the duplicate case, but never says when to choose this over schedule_run or a program/routine path, nor when not to use it. Usage is inferable from behavior rather than stated as guidance.

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