Skip to main content
Glama

Generate new workouts

generate_workouts
Read-only

New workouts from our generator (no AI), as text: built from patterns counted in thousands of real workouts, for a training style, minutes, kit and who trains. Nothing is saved; other ones each call.

Example, two people with an echo bike, rower and ski erg, 40-60 min:
generate_workouts(count=5, people=2, partner=True, minutes_min=40,
minutes_max=60, equipment=["echo-bike", "row-ergometer", "ski-erg"])

A shortfall says what blocked it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "generate_workouts"
  }
}

Input Schema

NameRequiredDescriptionDefault
sexNoWho trains, for the weights and machine doses: "men", "women", or "mixed" (a man and a woman together: each at their own; Hyrox stations at the mixed doubles race load). Omitted when the user did not say: every line reads both, men's/women's ("9/6 kg", "12/10 kcal"). Anything but men gets only workouts with a women's weight on every loaded line. Example: "women".
countNoHow many workouts, at most 5. Example: 3.
levelNoLevel 1 to 3, 3 the toughest. 1 scaled: dumbbells, kettlebells and sandbags a size lighter, barbells 0.7x Rx, easier skills (ring rows for pull-ups). 2 Rx and Hyrox Open. 3: a size heavier, barbells 1.25x Rx, Hyrox Pro, harder skills (chest-to-bar for pull-ups, legless rope climbs). Words in intent such as "pro", "open", "rx" or "scaled" set it too; 2 when none. Example: 3.
styleNoOnly this training style: running, hyrox, hybrid or crossfit. Any when omitted. Example: "hyrox".
formatNoOnly this format: for_time, amrap, emom, intervals. Any when omitted. Example: "amrap".
intentNoWhat the workout is for, in words: an intent (recovery, aerobic, long, threshold, vo2max, speed, test, compromised, strength-endurance, technique, partner) or a workout type ("fartlek", "tempo", "hero wod"). Several words keep what they share. Any when omitted. Example: "recovery".
peopleNoHow many train together with one of each machine. Above 1, only workouts they can share come back: partner workouts (taking turns on a station), workouts on no machine (side by side), or EMOMs/intervals with a different machine on every line and at least one line per person (start apart, rotate). Example: 2.
regionNoOnly this body region: "lower" (legs, hips, cardio), "upper" (push, pull, core, ski and row) or "core" (core, cardio). Words in intent such as "leg workout", "upper body" or "core" set it too. Example: "lower".
roundsNoExactly this many rounds: a for-time or interval workout repeated that often, an EMOM that many turns through its stations; never an AMRAP or a workout in parts. Words in intent such as "5 rounds" set it too. Example: 5.
excludeNoMovement slugs or names (from find_movements) every workout must leave out. Example: ["burpees"].
includeNoMovement slugs or names (from find_movements) every workout must hold; fewer come back the more are named. Example: ["wallballs"].
partnerNoTrue: only partner workouts (two people share the work). False: none. Omitted: either when people is above 1, else none. Example: true.
zone_maxNoEvery zone the work names at most this, 1-5. Example: 4.
zone_minNoEvery zone the work names at least this, 1-5; a workout naming no zone is left out. Words in intent such as "zones 2-4" set it too. Example: 2.
equipmentNoWhat the athletes have, as list_equipment keys or names ("echo-bike" or "echo", "row erg", "ski erg"), one item per entry. Say "1 dumbbell" or "1 kettlebell" when there is only one: movements needing a pair (farmers carry, dumbbell bench press) are left out. Other counts are ignored ("1 echo" is the echo bike): say how many train in people. Movements needing anything else (a bench press needs a bench) are left out; runs need "running" in the list. A name matching several keys or none is an error naming them. Example: ["1 dumbbell", "box", "ski-erg"]. Omitted is a full gym.
bodyweightNoFalse also leaves out movements needing no equipment (burpees, runs), so only the listed equipment is used. Example: false.
cap_minutesNoA time cap the workout must fit, in whole minutes: no printed cap passes it. Words in intent such as "time cap 30" set it too. Example: 30.
minutes_maxNoLongest estimated workout length, in minutes. Example: 25.
minutes_minNoShortest estimated workout length, in minutes. Example: 10.
show_scoresNoTrue adds a line of scores under each workout: can do it (%, the share of gym-goers who finish it as written), hard (0-100, how close the median gym-goer gets to their limit) and load (minutes x effort), and against the workout it was made from: stimulus (0-1, CrossFit's stimulus kept, with the levers changed), work (x the seed's), mix shift (how far the work moved between movement patterns), design (0-1) and, for Hyrox workouts, race fidelity (0-1). Off unless asked. Example: true.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • addedInput schema / properties / cap_minutes
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maximum": 240,
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "A time cap the workout must fit, in whole minutes: no printed cap passes it. Words in intent such as \"time cap 30\" set it too. Example: 30.",
      +  "title": "Cap Minutes"
      +}
    • addedInput schema / properties / intent
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 100,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "What the workout is for, in words: an intent (recovery, aerobic, long, threshold, vo2max, speed, test, compromised, strength-endurance, technique, partner) or a workout type (\"fartlek\", \"tempo\", \"hero wod\"). Several words keep what they share. Any when omitted. Example: \"recovery\".",
      +  "title": "Intent"
      +}
    • addedInput schema / properties / level
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maximum": 3,
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Level 1 to 3, 3 the toughest. 1 scaled: dumbbells, kettlebells and sandbags a size lighter, barbells 0.7x Rx, easier skills (ring rows for pull-ups). 2 Rx and Hyrox Open. 3: a size heavier, barbells 1.25x Rx, Hyrox Pro, harder skills (chest-to-bar for pull-ups, legless rope climbs). Words in intent such as \"pro\", \"open\", \"rx\" or \"scaled\" set it too; 2 when none. Example: 3.",
      +  "title": "Level"
      +}
    • addedInput schema / properties / partner
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "True: only partner workouts (two people share the work). False: none. Omitted: either when people is above 1, else none. Example: true.",
      +  "title": "Partner"
      +}
    • addedInput schema / properties / people
      Added value: +{
      +  "default": 1,
      +  "description": "How many train together with one of each machine. Above 1, only workouts they can share come back: partner workouts (taking turns on a station), workouts on no machine (side by side), or EMOMs/intervals with a different machine on every line and at least one line per person (start apart, rotate). Example: 2.",
      +  "maximum": 20,
      +  "minimum": 1,
      +  "title": "People",
      +  "type": "integer"
      +}
    • addedInput schema / properties / region
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 100,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Only this body region: \"lower\" (legs, hips, cardio), \"upper\" (push, pull, core, ski and row) or \"core\" (core, cardio). Words in intent such as \"leg workout\", \"upper body\" or \"core\" set it too. Example: \"lower\".",
      +  "title": "Region"
      +}
    • addedInput schema / properties / rounds
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maximum": 100,
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Exactly this many rounds: a for-time or interval workout repeated that often, an EMOM that many turns through its stations; never an AMRAP or a workout in parts. Words in intent such as \"5 rounds\" set it too. Example: 5.",
      +  "title": "Rounds"
      +}
    • changedInput schema / properties / show_scores / default
      Previous value: -trueNew value: +false
    • changedInput schema / properties / show_scores / description
      Previous value: -"True adds a line of scores under each workout: feasibility (0-100, can it be done as written), difficulty (0-100, the chance of not finishing inside the cap), and against the workout it was made from: stimulus (0-1, CrossFit's stimulus kept, with the levers changed), work (x the seed's), mix shift (how far the work moved between movement patterns), design (0-1) and, for Hyrox workouts, race fidelity (0-1). Example: false."New value: +"True adds a line of scores under each workout: can do it (%, the share of gym-goers who finish it as written), hard (0-100, how close the median gym-goer gets to their limit) and load (minutes x effort), and against the workout it was made from: stimulus (0-1, CrossFit's stimulus kept, with the levers changed), work (x the seed's), mix shift (how far the work moved between movement patterns), design (0-1) and, for Hyrox workouts, race fidelity (0-1). Off unless asked. Example: true."
    • addedInput schema / properties / style
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 100,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Only this training style: running, hyrox, hybrid or crossfit. Any when omitted. Example: \"hyrox\".",
      +  "title": "Style"
      +}
    • addedInput schema / properties / zone_max
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maximum": 5,
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Every zone the work names at most this, 1-5. Example: 4.",
      +  "title": "Zone Max"
      +}
    • addedInput schema / properties / zone_min
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maximum": 5,
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Every zone the work names at least this, 1-5; a workout naming no zone is left out. Words in intent such as \"zones 2-4\" set it too. Example: 2.",
      +  "title": "Zone Min"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly=true, destructive=false and idempotent=false; the description adds real context on top: a deterministic non-AI generator, no persistence ('Nothing is saved'), fresh results on each call, and failure behavior ('A shortfall says what blocked it'). It doesn't describe result shape, but an output schema exists so that burden is covered elsewhere.

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?

Front-loaded with purpose and the no-save constraint, then a single compact example, with no filler. Some phrasing is compressed to the point of awkwardness ('other ones each call', 'for a training style, minutes, kit and who trains'), which costs a little readability.

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 20-parameter generator with full schema coverage, annotations, and an output schema, the description covers the essential non-schema facts: statelessness, variability across calls, and what happens on a shortfall. Nothing critical is missing, though a brief note on ordering/pagination at count>5 isn't needed since count is capped.

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 worked example goes beyond it by showing how parameters interact (people=2 with partner=True and a three-item equipment list under a 40-60 minute window), which is the kind of combination the schema alone doesn't illustrate. It adds moderate value without re-documenting individual fields.

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 ('New workouts from our generator'), plus what they are built from ('patterns counted in thousands of real workouts') and what they are parameterized by (style, minutes, kit, who trains). 'Nothing is saved; other ones each call' distinguishes it from report_workout, which the sibling name implies persists something.

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?

Clear about the context of use (fresh, unsaved workouts each call) and points at the related tools by name where relevant (find_movements for include/exclude, list_equipment keys for equipment). It lacks an explicit 'use X instead when you want a saved/logged workout' statement, so the routing against report_workout is inferred rather than stated.

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