Skip to main content
Glama
smart-gym-mcp
by sla1k

smartgym_create_program

Destructive

Create and validate complete SmartGym routines with goals, warmup, exercises, and cooldown; save them to the server so all synced devices receive the program.

Instructions

Create one or more routines (a program) on the SmartGym server — all devices get them.

Each routine: name (must not match an active routine), goal (required free text, e.g.
"Strength" — the app can't save a routine without one), optional days/note, and three
ordered sections — `warmup` (optional), `exercises` (= main, required), `cooldown`
(optional). Each exercise: catalog name or id, optional rest_seconds, note and template
sets. Validation is all-or-nothing; dry_run=false creates the routines and verifies them
on the server.

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": {
      "routines": "<routines>"
    },
    "name": "smartgym_create_program"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
routinesYes

Output Schema

NameRequiredDescriptionDefault
planYes
noticeYes
createdYes
dry_runYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.1.0
    • changedInput schema / $defs / ExerciseSpec / properties / rest_seconds / anyOf
      Previous value: -[
      -  {
      -    "minimum": 0,
      -    "type": "integer"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "description": "Rest between sets, in seconds",
      +    "minimum": 0,
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / $defs / ExerciseSpec / properties / sets / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "$ref": "#/$defs/SetSpec"
      -    },
      -    "minItems": 1,
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "description": "Template sets [{reps, weight_kg}], in order",
      +    "items": {
      +      "$ref": "#/$defs/SetSpec"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / $defs / ExerciseSpec / properties / sets / description
      Previous value: -"Template sets; omitted = one default set (flagged in dry-run)"New value: +"Omitted = one default set (flagged in the dry run)"
    • changedInput schema / $defs / RoutineSpec / properties / days / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "enum": [
      +        1,
      +        2,
      +        3,
      +        4,
      +        5,
      +        6,
      +        7
      +      ],
      +      "type": "integer"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / $defs / RoutineSpec / properties / days / description
      Previous value: -"Days: comma-separated weekday numbers, 1 = Sunday, 2 = Monday … 7 = Saturday (e.g. \"2,4,6\"); \"\" clears"New value: +"Weekdays, 1 = Sunday, 2 = Monday … 7 = Saturday (e.g. [2, 4, 6]); [] clears"
    • removedInput schema / $defs / RoutineSpec / properties / goal / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / $defs / RoutineSpec / properties / goal / default
      Removed value: -null
    • addedInput schema / $defs / RoutineSpec / properties / goal / description
      Added value: +"Free text, e.g. \"Strength\"; must not be blank"
    • addedInput schema / $defs / RoutineSpec / properties / goal / type
      Added value: +"string"
    • changedInput schema / $defs / RoutineSpec / required
      Previous value: -[
      -  "name",
      -  "exercises"
      -]New value: +[
      +  "name",
      +  "goal",
      +  "exercises"
      +]
    • changedInput schema / $defs / SetSpec / properties / reps / description
      Previous value: -"Target reps for this set"New value: +"Target reps for this set; for a timed exercise (e.g. Plank, Dead Hang) the duration in seconds"
  2. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations (destructive=true, idempotent=false), it discloses device-wide propagation, the uniqueness constraint that a name must not match an active routine, the all-or-nothing validation model, and that dry_run=false triggers server-side verification. That is genuinely useful mutation context. What it does not cover is what a name collision or failed verification returns, so it falls short of a full 5.

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 description is front-loaded with the core action, then fans out into the routine and exercise shapes in the same order the schema nests them. Sentences are dense but every one carries a constraint or field meaning; the nesting recap is long but justified given the empty top-level schema descriptions.

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, nested-object creation tool the description supplies the required fields, ordering rules, uniqueness constraint, validation model, and dry-run semantics, and an output schema exists to handle return values. An agent has everything needed in order to construct a valid call and predict what happens on success versus validation failure.

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?

Top-level schema description coverage is 0% (dry_run and routines carry no descriptions), so the description must carry the weight, and it does: it explains the ordered warmup/exercises/cooldown sections, that exercises is the required main section while the others are optional, the exercise fields (catalog name or id, rest_seconds, note, template sets), and the meaning of dry_run. It omits the weekday encoding for days, though the schema itself documents that field.

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 sentence names a specific verb and resource (create routines/a program) and adds scope that matters: the routines land on the SmartGym server and propagate to all devices. It then enumerates the shape of a routine, so an agent can tell this apart from smartgym_update_routine or smartgym_apply_routine without opening the schema.

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?

The closing clause establishes the working flow: validation is all-or-nothing and dry_run=false is what actually creates and verifies routines, which implies the default dry run is a safe pre-flight. It does not state when to prefer update_routine over recreating an existing routine, so there is clear context but no explicit exclusions or alternatives.

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