Skip to main content
Glama

Povver — Strength Training

Analyze Training

analyze_training
Read-only

By view. strength_climb: am I getting stronger (8 weeks) · insights: weekly review, volume, fatigue (check partial_week) · muscle_state (muscle_group, omit for all): volume zone, fatigue, plateau · muscle_group_progress (muscle_group, weeks): weekly series · exercise_progress (exercise_id, exercise_name or exercise_ids, weeks): one lift's trend, PRs, bests · sets: raw sets, filtered, paged · trained_exercises: exact ids from the newest 800 sets (window.scan_capped = older lifts missing; truncated = trimmed list) · status (weeks): adherence, next workout · recommendations (include_all).

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": {
      "view": "<view>"
    },
    "name": "analyze_training"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
viewYes
limitNoMax results (1-200).
weeksNoWeeks (1-52).
cursorNosets: next_cursor; keep every other argument the same.
muscleNosets: a specific muscle.
exercise_idNoExact exercise id.
include_allNorecommendations: also applied, rejected, expired.
exercise_idsNoUp to 10 exact ids.
muscle_groupNochest, back, shoulders, quads, hamstrings, glutes, biceps, triceps, calves or abs
exercise_nameNoFuzzy name; check meta.resolution / resolution in the answer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish readOnly/non-destructive/closed-world, so the bar is lower, and the description still adds real context: the newest-800-sets window for trained_exercises, the meaning of window.scan_capped and truncated, the partial_week flag on insights, and the cursor rule of keeping every other argument identical. These are caveats an agent could not infer from structured fields. It does not cover error behavior or the shape of per-view responses beyond a keyword list.

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 a single front-loaded clause followed by a scannable bullet list separated by '·', one per view, with no filler sentences. The telegraphic register ('PRs, bests', 'adherence') is dense and occasionally requires a second read, which costs it the top score, but nothing is redundant.

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 nine-way dispatch tool with eleven parameters and no output schema, the description covers every view, the key flags returned inside responses (partial_week, scan_capped, truncated, meta.resolution), and which parameter belongs to which view. That is exactly the information an agent needs to choose a view and call it correctly; the remaining detail lives in the well-covered schema.

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 schema coverage at 82% the baseline is 3, but the description adds cross-parameter applicability the schema cannot express: which view consumes muscle_group, which consumes weeks, that exercise_progress takes exercise_id, exercise_name OR exercise_ids, and that include_all only affects recommendations. Sort, limit and muscle filtering are left to the schema. This is a meaningful step above the baseline.

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 description opens with 'By view' and then enumerates all nine view values, each with a short statement of what it returns (strength trend, weekly review, volume zone/fatigue/plateau, PRs and bests, raw sets, adherence). An agent can tell exactly what the tool produces and how to select a mode without opening the schema. It stops short of a single stated purpose sentence and never explicitly contrasts with siblings like read_workouts or get_context, so it is clear but not maximally differentiated.

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?

Each view is framed as a question it answers ('am I getting stronger', 'weekly review', 'one lift's trend'), which is genuine when-to-use guidance at the view-selection level, and caveats such as 'check partial_week' and 'omit for all' steer correct invocation. What is missing is any guidance on when to prefer this tool over the read_* siblings or on cost/latency tradeoffs between views, so there is no explicit exclusion or alternative routing.

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.