Skip to main content
Glama

save_workout_template

Store reusable cycling, running, or interval workouts as templates in your Coros library, ready to sync to your watch for guided training.

Instructions

Save a REUSABLE cycling/intervals/running workout TEMPLATE to the Coros library.

⚠️ This persists to the library indefinitely. Use ONLY when the user explicitly asks to "save as a template", "create a workout in my library", "add to my workout list", or otherwise indicates they want a reusable template.

For a ONE-OFF workout for a specific date — the common case — use schedule_workout instead. That tool builds the workout inline and leaves no library residue.

If the user's intent is unclear, ASK THEM: "Do you want this saved as a reusable template in your library, or just scheduled as a one-off for [date]?" Don't guess.

The saved template appears in the Coros app under Workouts and can be synced to the watch for guided execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesWorkout name (e.g. "Z2 Erholung 60min").
stepsYesList of workout steps. Each step is either a plain step or a repeat group. Plain step: - name (str): step label, e.g. "10:00 Warm-up" - duration_minutes (float) OR duration_meters (float): step length, time-based or distance-based. Use duration_meters for a step that should end at a real distance regardless of pace (e.g. "1000" for a 1km rep) rather than an estimated time -- a duration_minutes step ends after that much elapsed time even if actual pace made it cover more or less than the intended distance. Exactly one of the two is required. - intensity_low (int): lower intensity target (watts, BPM, etc. depending on intensity_type) - intensity_high (int): upper intensity target (0 = open-ended) Note: power_low_w / power_high_w are accepted as legacy aliases for intensity_low / intensity_high. Repeat group (for intervals): - repeat (int): number of repetitions - steps (list[dict]): sub-steps (same format as plain steps) Example: [
sport_typeNoSport type ID, in the ACTIVITY namespace (the same IDs list_activities returns). Default 2 = Indoor Cycling (indoor trainer). - Cycling: 2 = Indoor Cycling (indoor trainer), 200 = Road Bike (outdoor), 201 = Indoor Cycling (alt) - Running: 100 = Running, 102 = Trail Running, 103 = Track Running Running IDs are mapped internally to the workout-API wire ID (sportType=1) and given the metadata block COROS requires for runs. Do NOT pass 1 directly — it's the internal wire ID and is rejected.
intensity_typeNoIntensity type ID. Defaults per sport when omitted: runs → 2 (HR), cycling → 6 (power in watts). Other IntensityType values: 1=weight, 2=HR, 3=pace, 4=speed, 5=none, 6=power, 7=cadence

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changedv0.1.1
    • changedInput schema / properties / steps / description
      Previous value: -"List of workout steps. Each step is either a plain step or a repeat group.\n\nPlain step:\n- name (str): step label, e.g. \"10:00 Warm-up\"\n- duration_minutes (float): step duration in minutes\n- intensity_low (int): lower intensity target (watts, BPM, etc. depending on intensity_type)\n- intensity_high (int): upper intensity target (0 = open-ended)\nNote: power_low_w / power_high_w are accepted as legacy aliases for intensity_low / intensity_high.\n\nRepeat group (for intervals):\n- repeat (int): number of repetitions\n- steps (list[dict]): sub-steps (same format as plain steps)\n\nExample:\n["New value: +"List of workout steps. Each step is either a plain step or a repeat group.\n\nPlain step:\n- name (str): step label, e.g. \"10:00 Warm-up\"\n- duration_minutes (float) OR duration_meters (float): step length,\n  time-based or distance-based. Use duration_meters for a step that\n  should end at a real distance regardless of pace (e.g. \"1000\" for\n  a 1km rep) rather than an estimated time -- a duration_minutes\n  step ends after that much elapsed time even if actual pace made it\n  cover more or less than the intended distance. Exactly one of the\n  two is required.\n- intensity_low (int): lower intensity target (watts, BPM, etc. depending on intensity_type)\n- intensity_high (int): upper intensity target (0 = open-ended)\nNote: power_low_w / power_high_w are accepted as legacy aliases for intensity_low / intensity_high.\n\nRepeat group (for intervals):\n- repeat (int): number of repetitions\n- steps (list[dict]): sub-steps (same format as plain steps)\n\nExample:\n["
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations indicate readOnlyHint=false and destructiveHint=false, but the description goes further by disclosing that this 'persists to the library indefinitely', appears in the Coros app under Workouts, and can be synced to the watch. This adds real behavioral context beyond the annotations and does not contradict them.

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?

Although the description is longer than average, every section earns its place: purpose, persistence warning, sibling alternative, user-disambiguation prompt, and post-save outcome. The critical caveat is front-loaded with a warning symbol, and the structure is easy to scan.

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?

The description is complete for a high-stakes persistence operation: it explains side effects, required user intent, alternatives, and disambiguation. With a rich input schema and an output schema present, nothing essential for correct invocation is missing.

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

Parameters3/5

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

The tool description itself adds little parameter-level detail, but the input schema already provides thorough coverage of all parameters, including sport_type wire-ID mappings and intensity_type defaults. At 100% schema coverage, the baseline of 3 applies; no additional parameter semantics are needed.

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 description opens with a precise verb and resource: 'Save a REUSABLE cycling/intervals/running workout TEMPLATE to the Coros library.' It clearly distinguishes this from one-off scheduling and names the sibling tool, schedule_workout, making the purpose unambiguous.

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?

It explicitly states when to use the tool ('only when the user explicitly asks to save as a template'), when not to use it (one-off workout: use schedule_workout instead), and instructs the agent to ask the user when intent is unclear. This is exemplary routing guidance.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cygnusb/coros-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server