Skip to main content
Glama

create_workout_plan

Create a workout plan for a client (confirm-gated). To check whether one was already created — for example if asked "is it done?" — call list_workout_plans instead of calling this again; re-running this with confirm: true a second time for the same client and title returns the plan already on file rather than writing a duplicate. exercises: array of { name, sets, reps, restSeconds?, section?, exerciseId?, notes?, modality?, supersetGroup?, ... }. reps is a number or a range like "8-10" (saved as a range; the app shows 8-10). supersetGroup: same label ("A", "B") = done back to back. modality selects which parameters actually describe the work: STRENGTH (sets/reps/restSeconds) | INTERVAL (rounds + distanceMeters or durationSeconds + recoverySeconds + targetPace) | STEADY (durationSeconds or distanceMeters + targetPace) | AMRAP or EMOM (durationSeconds as the cap + rounds) | FOR_TIME | HOLD (durationSeconds). Never describe a run as sets and reps: '6 x 400 m at 5k pace, 90 s jog' is modality INTERVAL with rounds 6, distanceMeters 400, recoverySeconds 90, targetPace '5k pace'. Call get_training_split first so the week has a real structure. section must be one of WARMUP | RESISTANCE | STRETCHING | CARDIO | COOL_DOWN (defaults to RESISTANCE so the app renders them under 'Main Workout'). exerciseId: pass the id from search_exercises when there's a confident catalog match — this is what makes the exercise show an image/video to the client. notes: one short sentence explaining why this exercise is in the plan — shown to the client under the exercise. days: optional [MONDAY..SUNDAY].

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": {
      "clientId": "<clientId>",
      "title": "<title>",
      "startDate": "<startDate>",
      "exercises": "<exercises>"
    },
    "name": "create_workout_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
titleYes
confirmNoMust be true to actually execute. If false/omitted, returns a preview only.
endDateNo
clientIdYes
exercisesYes
startDateYesYYYY-MM-DD
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation profile is known. The description adds genuinely non-obvious behavior: the confirm gate and, more importantly, idempotency — repeating the call for the same client and title returns the existing plan rather than writing a duplicate. It does not discuss permissions, validation failures, or partial-failure behavior, so it falls short of a 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?

It is front-loaded (purpose, then sibling routing, then parameter semantics) and every sentence carries information, but the parameter block is a single dense paragraph that would scan better as short labeled lines. No filler sentences, though.

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 an 8-parameter mutation tool with nested payloads, no output schema, and no enums in the schema, the description covers the complex parts thoroughly. It is thin on clientId, startDate/endDate, and description, and says nothing about what happens on validation failure, but those are secondary for a competent agent.

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?

Schema coverage is only 25% and the exercises items object is an unschematized additionalProperties:{} bag, so the description carries the burden — and it does, explaining reps-as-range, supersetGroup, exerciseId's effect on client-visible media, notes, section enum with its RESISTANCE default, days, and a full modality-to-parameter mapping with a worked interval example. This is meaning well beyond anything the schema conveys.

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 names a specific verb and resource ('Create a workout plan for a client') plus a non-obvious constraint (confirm-gated), and the text explicitly distinguishes this from list_workout_plans and get_training_split. An agent can tell what this tool does and what it is not 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit routing rules: use list_workout_plans to check whether a plan already exists (e.g. 'is it done?'), call get_training_split before creating so the week has structure, and use search_exercises to obtain exerciseId. It also states the when-not case for re-running with confirm: true, so alternatives and exclusions are both covered.

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.