Skip to main content
Glama

Good Turn Studio (all tools)

by io.github.GoodTurnStudio
OverviewDiscussionsAdmin

Plan My Workout: A weekly workout plan with sets, reps and rest

planmyworkout_get_workout_plan
Read-onlyIdempotent

Plan My Workout. A weekly workout plan with sets, reps and rest. For requests like "make me a 3 day beginner gym plan", "home workout with just dumbbells, 30 minutes", "a 5 day muscle building split", "I have a pull-up bar and dumbbells", "a 20 minute workout" (days=1 gives a single session), "a workout plan to lose weight", "couch to 5K" or "a 10K running plan" (a 10K or longer goal gets the build-up plan unless the user says they are a beginner), or "give me another one" (the same inputs with seed plus one). Takes either the fields, or the user's words in q, from which the service reads days, minutes, level, goal and equipment from them. Fields win over q. Running plans also return weeks: every week's sessions (a 9-week walk-run build to 30 minutes of running for beginners; easy, interval, tempo and long runs for intermediates), with week 1 laid out in days.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoThe user's request in their own words, for example "3 day beginner gym plan, 45 minutes".
daysNoDays per week, 1 to 6 (1 gives a single session). More than 6 (or "every day") is planned as 6 with a rest day, and the answer says so in say and in plan.days_asked and plan.days_note. Default 3.
goalNoGoal: strength, muscle, general (default), conditioning (covers fat loss or weight loss requests), running or mobility.
seedNo0 to 9999. Change it for a different mix of exercises with the same setup. Default 0.
levelNoLevel: beginner (default) or intermediate. Advanced is treated as intermediate.
countryNoTwo-letter country code for kit links (US, GB, IE, CA, AU). Defaults to the visitor's country.
minutesNoMinutes per session including warm-up, 15 to 120. Default 45.
equipmentNoComma separated: none (default), dumbbells, barbell, gym, bands, kettlebell, pullupbar (a pull-up bar), jumprope.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / goal / description
      Previous value: -"strength, muscle, general (default), conditioning (use this for fat loss or weight loss requests), running or mobility."New value: +"Goal: strength, muscle, general (default), conditioning (covers fat loss or weight loss requests), running or mobility."
    • changedInput schema / properties / level / description
      Previous value: -"beginner (default) or intermediate. Advanced is treated as intermediate."New value: +"Level: beginner (default) or intermediate. Advanced is treated as intermediate."
  2. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description does add real behavior beyond that: the seed increment trick for repeat requests, the days>6 capping with a note surfaced in say and plan.days_asked/days_note, and advanced being treated as intermediate. However, it doesn't disclose the shape of the returned plan or whether generated plans are stable across identical calls (relevant given idempotentHint).

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?

Purpose is front-loaded in the first two sentences before the example list. The long parenthetical example block is justified for a natural-language-driven tool, but the run-on sentence structure makes the routing rules harder to scan than they need to be.

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?

With 8 optional parameters, no output schema and no required fields, the description carries what the agent needs: it explains input precedence, edge-case handling, output shape at a high level (plan with sets/reps/rest; running plans return per-week sessions with week 1 laid out), and points at output fields that report deviations.

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 parameters are already documented and the baseline would be 3. The description adds genuine semantics on top: q-versus-fields precedence, days=1 collapsing to a single session, seed reuse for another mix, and goal 'conditioning' covering fat/weight-loss wording. Only the country parameter is left entirely to the schema.

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: it produces a weekly workout plan with sets, reps and rest, and the example phrasings make the scope unmistakable against the exercise-lookup siblings (get_exercise, list_exercises). An agent can tell what it produces 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?

Gives explicit when-to-use examples covering the main request shapes, plus precise routing rules: 'Fields win over q', 'days=1 gives a single session', days>6 is planned as 6 with a rest day, longer running goals get the build-up plan unless the user self-identifies as beginner, and 'give me another one' means the same inputs with seed plus one.

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

All Good Turn Studio (all tools) toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources