Skip to main content
Glama

unschedule_workout

DestructiveIdempotent

Remove one entry from the user's calendar by its schedule_id: a workout scheduled for a single date, or a run. It also leaves the user's Garmin calendar. Saved workout templates are not changed; a run is gone. Occurrences created by the weekly routine or a program are refused and can only be changed in the LiftTrack app. workout_name and date must be the entry's own, as the schedule lists them; a mismatch is refused. If the same workout stays on that date (from the weekly routine, a program, or another one off), the result reports what holds it in still_scheduled_by.

Args: schedule_id: The entry's id from the schedule. Never show it to the user. workout_name: The entry's workout name. date: YYYY-MM-DD of the entry, today or later. Past entries are kept as the user's training record.

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": {
      "schedule_id": "<schedule_id>",
      "workout_name": "<workout_name>",
      "date": "<date>"
    },
    "name": "unschedule_workout"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesThe entry's date as YYYY-MM-DD
schedule_idYesThe entry's schedule_id, as the schedule lists it
workout_nameYesThe entry's workout name, as the schedule lists it

Output Schema

NameRequiredDescriptionDefault
dateYes
kindYes
workout_idNoThe saved workout the removed entry scheduled; absent for a run.
schedule_idYes
workout_nameYes
removed_countYes
still_scheduled_byNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / workout_id
      Added value: +{
      +  "description": "The saved workout the removed entry scheduled; absent for a run.",
      +  "type": "string"
      +}
  2. Changed8 schema fields changed
    • changedInput schema / properties / date / description
      Previous value: -"Calendar date as YYYY-MM-DD"New value: +"The entry's date as YYYY-MM-DD"
    • addedInput schema / properties / schedule_id
      Added value: +{
      +  "description": "The entry's schedule_id, as the schedule lists it",
      +  "type": "string"
      +}
    • 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"
      -}
    • changedInput schema / properties / workout_name / description
      Previous value: -"The exact name of the workout template"New value: +"The entry's workout name, as the schedule lists it"
    • changedInput schema / required
      Previous value: -[
      -  "workout_name",
      -  "date"
      -]New value: +[
      +  "schedule_id",
      +  "workout_name",
      +  "date"
      +]
    • addedOutput schema / properties / kind
      Added value: +{
      +  "enum": [
      +    "workout",
      +    "endurance"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / schedule_id
      Added value: +{
      +  "type": "string"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "workout_name",
      -  "date",
      -  "removed_count"
      -]New value: +[
      +  "schedule_id",
      +  "kind",
      +  "workout_name",
      +  "date",
      +  "removed_count"
      +]
  3. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes further: it names the collateral effect (leaves the user's Garmin calendar), states what is preserved (saved templates), and explains the refusal semantics on mismatch. It also notes the result surfaces still_scheduled_by when the workout remains on that date via another source.

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?

The destructive action and its target are front-loaded in the first sentence, and every subsequent sentence carries distinct information. Some phrasing is dense and slightly awkward ('a run is gone', 'what holds it in still_scheduled_by'), which costs a point but does not obscure meaning.

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 destructive, three-required-parameter mutation, the definition covers target identification, matching requirements, refusal cases, side effects, and preserved state. An output schema exists, so the brief mention of still_scheduled_by is sufficient without documenting the full return shape.

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?

Although schema coverage is 100%, the description adds meaning the schema does not: workout_name and date must match the entry's own values as the schedule lists them, a mismatch is refused, date must be today or later, and schedule_id must never be shown to the user. These are caller-relevant constraints absent from the JSON 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 opening clause states a specific verb and resource — 'Remove one entry from the user's calendar by its schedule_id' — and immediately disambiguates from the template tool by asserting 'Saved workout templates are not changed'. It further scopes the target to a single-date workout or run, leaving no ambiguity against delete_workout or update_workout.

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?

Explicit when-not conditions are given: occurrences created by the weekly routine or a program 'are refused and can only be changed in the LiftTrack app', past entries are kept, and mismatched name/date is refused, each pointing the agent elsewhere. This is real routing guidance rather than implied usage.

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