Skip to main content
Glama

Set today's session

set_today_session
Destructive

Writes the session the athlete will do today or tomorrow (date must be one of those, in the athlete's time zone). Give blocks (kind back (shown as Foundation), strength, mobility or other) of items, each an exercise id from list_exercises with a prescription (method reps, hold or time; sets; bothSides; restSeconds; optional weightKg and cue). bothSides plays each set Left then Right; it must match the exercise's sides in list_exercises (together → false, each → true), or the write is rejected. Each exercise has a kind; put it in a block of that kind (an exercise without a kind goes in an other block). timeBudgetMinutes is optional: how long the athlete has. coachNote is shown to the athlete on Today. The server owns the session's id, revision, status, change list and time estimate and fills them in. The prescription is stored as written: the server does not apply the athlete's rules, cap load or adjust for pain. An item above its ladder's current level is set to that level and listed in changes; preview is what Today will show. A session that has started, finished or been abandoned can't be replaced. A rejected write returns every reason. To split the day, send parts instead of blocks: 2–3 parts with a label each (e.g. Morning, Afternoon) and their own blocks (coachNote and timeBudgetMinutes go on each part, not the top level); the whole day stays within 90 minutes and each exercise once. Started parts are kept. Sending blocks to a split day merges it back into one session (not allowed once a later part has started); a day whose one session has started can't be split. parts in the result says which parts were written, kept and withdrawn. For a superset or circuit, put its exercises in their own block with rounds: true: the app plays set 1 of each in order, then set 2 of each. Rest after a set is that item's restSeconds, so give every item but the last 0 (or a short walk-over) and the last the rest between rounds. Set counts may differ; an item with fewer sets drops out of the later rounds. In a round where the last item has dropped out, the rest after the round is the rest of the last item still playing. A rounds block needs 2 or more exercises; with one it is played as straight sets.

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": {
      "date": "<date>"
    },
    "name": "set_today_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYes
partsNo
blocksNo
coachNoteNo
timeBudgetMinutesNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say this is a destructive, non-idempotent write; the description adds substantial context beyond that: the server owns id/revision/status/change list/time estimate, the prescription is stored as written without rule or load capping, above-level items are clamped and reported in `changes`, `preview` shows what Today will render, and rejected writes return every reason. Split/merge semantics for parts and round-by-round superset playback with rest accounting are also disclosed.

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?

Nearly every sentence earns its place given the tool's complexity, but it is delivered as a single dense paragraph, with the split-day and rounds/superset mechanics buried mid-text. Bullets or clearer front-loading of the core blocks-vs-parts choice would improve scanability without losing content.

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?

Covers the full lifecycle an agent needs: date window, block/item structure, bothSides validation against list_exercises, ladder clamping, rejection behavior, split-day and merge rules, superset rest semantics, and which fields the server assigns. Return-shape cues (`changes`, `preview`, `parts`) compensate for the absent output 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 0% schema description coverage, the description carries the burden and mostly succeeds: it explains `date`, block `kind` values (with back shown as Foundation), item `exerciseId`, the prescription fields (method reps/hold/time, sets, bothSides, restSeconds, weightKg, cue), `timeBudgetMinutes`, `coachNote`, `parts` with per-part notes and the 90-minute/one-exercise-once limits, and `rounds`. It leaves the required block `name` and the item-level `id` unexplained, so a couple of schema fields remain opaque.

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 — 'Writes the session the athlete will do today or tomorrow' — with an explicit date scope that separates it from program-scheduling siblings and from get_today. An agent knows immediately this is the write path for the current/imminent training day.

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?

Gives clear when-not conditions (a session that has started, finished or been abandoned can't be replaced; a day whose one session has started can't be split or merged back), and routes exercise ids to list_exercises. It stops short of naming the alternative tool for dates beyond tomorrow, leaving the agent to infer the routing from the date constraint.

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