Skip to main content
Glama

push_plan

Validate and save an athlete's workout plan, then schedule it on the Apple Watch for the chosen date and time.

Instructions

Validates a session (sport one of run, indoor_run, walk, hike, cycle, indoor_cycle, pool_swim, open_water_swim, indoor_row, hiit, elliptical; labels under 40 characters, zones 1 to 5, positive goals) and writes it to plans/. Set scheduled_for to the day and time the athlete will do it: the app schedules it on the Watch for that time (one tap in the Import tab, or automatically when the athlete switched that on). Ask the athlete before you write one.

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": {
      "plan": "<plan>"
    },
    "name": "push_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
planYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations it discloses the validation rules the payload must satisfy, the downstream side effect (the app schedules the workout on the Watch for scheduled_for, one tap in the Import tab or automatic), and the defaulting behavior (next morning at 10:00 when scheduled_for is missing or past). The notable gap is duplicate handling: idempotentHint=false implies repeated calls create additional plans, but the description never says so or explains how an existing plan at that time is treated.

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?

Three front-loaded sentences: purpose, scheduling semantics, then the consent rule. The parenthetical constraint list is long but readable, and repeating the sport enumeration already present in the schema description is mild redundancy.

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

Completeness4/5

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

For a single, deeply nested mutation parameter with no output schema, the description covers validation, scheduling side effects, defaulting, and the consent requirement — enough for an agent to call it correctly. Completeness would be higher if it stated the return value or duplicate-creation behavior, which matters given non-idempotent, non-destructive annotations.

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?

Top-level schema coverage is 0% for the single 'plan' parameter, so the description must carry the meaning — and it does, adding constraints the schema does not surface as guidance (valid sport set, labels under 40 characters, zones 1 to 5, positive goals) and rich semantics for scheduled_for including its default behavior and its role in matching the executed workout. The sport enumeration and label length duplicate nested schema text, but the scheduling and validation context is genuinely additive.

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 ('validates a session ... and writes it to plans/') plus the destination, so the agent immediately knows this is the write path for session plans. That verb set is clearly distinguishable from the read-only siblings (list_plans, get_plan_status, get_workout) without opening any schema.

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 an explicit precondition — 'Ask the athlete before you write one' — and states the condition that makes scheduled_for meaningful ('Set scheduled_for to the day and time the athlete will do it'). It stops short of naming a read sibling to check first (e.g. list_plans to avoid duplicates), so it is clear but not fully routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.