Skip to main content
Glama

mywhoosh_create_workout

Create a custom MyWhoosh cycling workout from ordered blocks using %FTP power, cadence targets, repeats, and optional ERG mode to build structured training sessions.

Instructions

Create a custom cycling workout in MyWhoosh.

blocks are executed in order. Power in % FTP (e.g. 90 = 90% FTP). erg_mode=True: trainer holds the target power (ERG). False: rider controls resistance. ftp_watts is optional and only used to compute kJ. Text (name, description, messages) is transliterated to ASCII (ö->oe, ß->ss, – -> -), because MyWhoosh drops all non-ASCII characters.

Example blocks: {"type":"warmup","duration_s":600,"start_power":50,"end_power":75} {"type":"interval","duration_s":240,"power":105,"repeat":4,"rest_duration_s":180,"rest_power":55} {"type":"steady","duration_s":1200,"power":70,"cadence":90} {"type":"cooldown","duration_s":300,"start_power":65,"end_power":45}

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>",
      "blocks": "<blocks>"
    },
    "name": "mywhoosh_create_workout"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
blocksYes
erg_modeNo
ftp_wattsNo
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses block execution ordering, that power values are % FTP, what erg_mode actually changes on the trainer, that ftp_watts only affects kJ computation, and — importantly — that all text is transliterated to ASCII because MyWhoosh drops non-ASCII characters. It omits authorization requirements, uniqueness constraints on name, whether the workout is persisted to a library, and what is returned on success.

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 purpose is front-loaded in one sentence, followed by terse semantic notes and four worked example blocks that are genuinely useful for a nested, example-driven schema. Some notes (e.g. the transliteration parenthetical) are dense but each sentence carries information; nothing is redundant padding.

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?

For a creation tool with a five-parameter schema, a deeply nested block type, no annotations and no output schema, the description covers the essentials: ordering, units, mode semantics, and the ASCII-transliteration side effect. Gaps remain around success/failure behavior, returned identifiers, and how the new workout relates to scheduling, which matter for a tool that persists state.

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?

Top-level schema coverage is effectively 0% (name, blocks, erg_mode, ftp_watts, description have no inline descriptions), so the description must compensate. It adds real meaning for erg_mode and ftp_watts and clarifies power units, but leaves the name and description fields (and defaults like erg_mode=false) without comment, so coverage is partial rather than complete. The nested Block fields are documented in the schema itself, which limits how much credit the description earns there.

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?

The first sentence states a specific verb and resource ('Create a custom cycling workout in MyWhoosh'), which is unambiguous. It does not explicitly contrast with sibling tools such as mywhoosh_update_workout or mywhoosh_schedule_workout, so an agent must infer that 'create' means a new workout rather than editing or scheduling an existing one.

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 description explains how blocks are used ('blocks are executed in order') and when erg_mode should be True versus False, which is genuine usage guidance at the parameter level. However, it gives no guidance on when to call this tool versus mywhoosh_update_workout or mywhoosh_schedule_workout, and no prerequisites or constraints on creating a workout.

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