Skip to main content
Glama

Get athlete context

get_athlete_context
Read-onlyIdempotent

Returns the athlete's current training state, recent history and program. Takes no input.

Returned data:

  • Date: today (always the athlete's local date, not UTC) and timeZone, the athlete's time zone.

  • Program: name, coachBrief (what it's for), the body areas it tracks, trackPain (false: the app doesn't ask for pain levels) and custom (set when the athlete is on their own custom program). customPrograms lists their saved programs.

  • Schedule: schedule is the week: each weekday's day id and name, with parts (the part labels) on a day that repeats as a split.

  • Rules: programRules belong to the program, athleteRules to the athlete; rules combines them.

  • Profile: the athlete's profile. profile.intake, when present, holds their setup answers (days a week, session length, goal, equipment, what hurts).

  • Events: calendar events from a week ago onward.

  • Ladders: each ladder's level (0-based, here and in every tool), prescription, clean sessions so far and the usual number before stepping up, the baseline (the last prescription completed in full at that level, else the level's own) and lastChange (who moved it last; lastChange.by = athlete means the athlete changed the level themselves in the app).

  • Sessions: sessions from the last 14 days and any planned ahead, and a per-day summary of logged sets.

  • Feedback: session feedback (effort, note) and symptoms: the 0–10 level the athlete gave for each tracked body area when they finished a session.

  • skippedSets: by exercise, the sets passed with Skip exercise (it skips every set of the exercise not yet done).

  • exerciseNotes: what the athlete wrote about one exercise during the workout ("squats felt hard", "I can only do 20").

  • correctedSets (per summary): ladder and goal sets the athlete corrected at Finish, where they may fix a set the player got wrong (a hold timer stops at the target, so a longer hold is only recorded this way). Logs and summaries already show the corrected values; get_logs keeps the player's own number on each corrected set as loggedValue.

  • exerciseVideos: demo videos chosen for an exercise, by the athlete in the app (setBy athlete) or with set_exercise_video (setBy coach). The app plays them instead of the exercise's own video. Cleared choices aren't listed.

How the app behaves:

  • The app does not adjust anything for pain, rules, events, load or exercise notes: it plays each session exactly as written.

  • There is no pain input during a workout. A skipped set or a workout ended early (status abandoned, or sets with no log) is the sign something was avoided.

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_athlete_context"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent and closed-world, and the description adds substantially more: today is the athlete's local date not UTC, ladder levels are 0-based everywhere, corrected sets preserve loggedValue in get_logs, and exercise videos set in the app override the exercise's own video. It also discloses the important limitation that the app never adjusts for pain, rules, events, load or notes and that avoidance shows up as skipped sets or abandoned sessions. That is exactly the behavioral context annotations cannot carry.

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 purpose is front-loaded, and the return payload is broken into labeled groups (Date, Program, Schedule, Rules, Profile, Events, Ladders, Sessions, Feedback, skippedSets, exerciseNotes, correctedSets, exerciseVideos) followed by an app-behavior section. It is long, but every block documents a distinct part of a large undocumented return value, so the length earns its place. A few lines, such as the explanation of hold timers, could be tightened.

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?

There is no output schema, so the description carries the full burden of describing the return payload, and it does so field group by field group, including edge cases like lastChange.by = athlete and empty customPrograms. Combined with the app-behavior notes, an agent has enough to interpret the response without guessing.

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?

With zero parameters the baseline is 4, and the description explicitly says it takes no input, which is sufficient. No further parameter meaning is needed or possible.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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: return the athlete's current training state, recent history and program, and notes it takes no input. That makes the scope clear without opening the schema. It stops short of naming siblings like get_today or get_logs, so an agent must infer why this snapshot differs from those narrower reads.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated: a zero-input, all-in-one snapshot suggests calling it at the start of a conversation. There is no explicit when-to-use/when-not-to-use guidance and no named alternative, so the agent has to infer that get_today or get_logs serve narrower needs.

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