Skip to main content
Glama

get_training_split

Read-only

Named training programme templates (Full-Body, PPL, Upper/Lower, 5x5, powerlifting peaking, HYROX, CrossFit metcon, hybrid athlete, Couch-to-5K, half/marathon, calisthenics, home minimal, senior, prenatal) with their day-by-day structure, who they suit, the progression rule and the cautions. Call this BEFORE create_workout_plan so the week is built on a real, named structure instead of one improvised from scratch. Search by name ('hyrox', 'ppl', 'couch to 5k') or by goal + daysPerWeek + experience. Each day lists the modalities it should use — build those sessions with matching modality on each exercise, never sets/reps for a run.

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": "get_training_split"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNoe.g. 'lose fat', 'build muscle', 'endurance'
limitNo
queryNoProgramme name, e.g. 'hyrox', 'ppl', 'marathon'
experienceNoBEGINNER | INTERMEDIATE | ADVANCED
daysPerWeekNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / default
      Previous value: -2New value: +5
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

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

The readOnlyHint/openWorldHint annotations already establish a safe local read, so the bar is lower. The description adds genuine value by disclosing the shape of returned content (day-by-day structure, suitability, progression rule, cautions) and the modality-matching constraint, but it says nothing about what happens with no arguments, how limit interacts with multiple matching templates, or result ordering/truncation.

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 critical guidance (call before create_workout_plan) arrives early and the modality caveat is a useful closer. However, the parenthetical list of fourteen programme names plus the two comma-separated search examples is bulky and could be trimmed to a few representative examples without losing selection value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does a reasonable job sketching the returned fields, but with five optional parameters and none required it never says what a no-argument call returns or how results are ranked/limited. For a reference-lookup tool that an agent may call bare, that behavioral gap matters, though the purpose, sequencing and downstream usage are otherwise well covered.

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?

At 60% schema coverage the description must compensate, and it does: it explains that query accepts informal names ('couch to 5k') and that goal, daysPerWeek and experience can be combined as an alternative retrieval path — a relationship the schema does not state. The limit parameter is left unmentioned, which keeps it below a 5.

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 resource — named training programme templates — and enumerates their contents (day-by-day structure, who they suit, progression rule, cautions) plus concrete examples of the template families. An agent can immediately tell this retrieves reference programmes, not user data, and the closing line distinguishes it from plan creation by routing structure into create_workout_plan.

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?

Explicitly says to call this BEFORE create_workout_plan and why ('so the week is built on a real, named structure instead of one improvised from scratch'), which is a real sequencing instruction relative to a named sibling. It also gives two search strategies (by name, or by goal + daysPerWeek + experience) and a downstream constraint for using the results (build sessions with matching modality, never sets/reps for a run).

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.