Skip to main content
Glama

Change a program day for every week

set_program_day
DestructiveIdempotent

Changes one day of the athlete's program for EVERY future week (for one date only, use set_today_session). dayId must be an existing day (see schedule in get_athlete_context) unless you pass create: true to add a new day. weekdays is optional: omitted, an existing day keeps its weekdays and a new day starts unscheduled; given, it is the day's full placement and weekdays it leaves become rest. Blocks use exercise ids from list_exercises; an exercise with a ladder leaves its prescription out. A day is at most 90 minutes. If the athlete is on a preset (Strong Back, Strong Knees), this first saves their own custom copy (default name " (custom)", or programName) and moves them onto it; their schedule and history stay. A rejected call changes nothing. Returns the program and a preview of the next date that plays the day. A coach session already written for a date still wins on that date. To make a day repeat as a split, send parts (2–3 labels, e.g. Morning, Afternoon) and a part (1-based) on every block, in part order; the whole day stays within 90 minutes and each exercise once. Omitting parts while blocks carry part is refused (send parts to keep a split, or drop part from every block to merge it). On the empty "Build with your coach" program the other program tools are refused until a day is scheduled with this tool (create: true and weekdays). 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": {
      "dayId": "<dayId>",
      "name": "<name>",
      "blocks": "<blocks>"
    },
    "name": "set_program_day"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
dayIdYes
partsNo
blocksYes
createNo
weekdaysNo
programNameNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds substantial context beyond them: a preset athlete gets a custom copy saved and keeps schedule/history, a rejected call changes nothing, a coach session written for a date overrides this, and the 90-minute cap applies. These are exactly the consequences an agent needs before mutating a program.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical scope distinction is front-loaded, but the rest is a single dense paragraph of backtick-fragmented clauses, and some content (round-robin rest when the last item drops out) reads like implementation trivia rather than selection guidance. It is information-dense rather than padded, but segmentation into sentences/blocks would make it far easier to parse.

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 7-parameter destructive mutation with nested block/prescription structure and no output schema, this covers the essentials: return value ('the program and a preview of the next date'), atomicity on rejection, preset migration, the split/rounds encoding rules, and a hard 90-minute limit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and largely does: dayId must exist unless create:true, weekdays is optional with different omitted-vs-supplied semantics (full placement, leftover weekdays become rest), programName overrides the '<Preset> (custom)' default, and parts/part interaction rules are spelled out including the refusal case. Only name, kind, weightKg and bothSides are left unexplained, mostly self-evident or bounded by 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?

The opening sentence gives a specific verb, resource and scope: it changes one program day for EVERY future week, and immediately contrasts that with set_today_session for a single date. An agent can pick this tool over its sibling without opening either 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?

Explicit routing conditions are given both ways: use set_today_session for one date, use create:true when the dayId doesn't exist yet, and on the empty 'Build with your coach' program this tool is the only one accepted until a day is scheduled. It also states hard preconditions (existing day, exercise ids from list_exercises) and what happens on a preset program.

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