Skip to main content
Glama
Sign In

TrainRec

by app.trainrec
OverviewDiscussionsAdmin

Set a reminder

trainrec_set_reminder

Reminders are TrainRec's notifications on the person's phone. They start at zero: none exist until the person asks their assistant (you) to set one up, so when they ask to be reminded of something, this is how. Adds a reminder, or changes one (give its id and version). Kinds: weigh_in, log_food (optionally one meal), workout (names today's planned workout if there is one) and streak (training weeks in a row, sent only if this week has no workout yet) go at a local time, and each is skipped that day once it is done. goal goes when a daily number is approaching or has reached its target (calories, a macro, or a nutrient with a target), not between 22:00 and 07:00. custom says the person's own words at a time. recap sends the day's calories and protein against their targets and its workout, at a time, every day it is on. Every reminder needs its trigger from the person: a time (their local time, 24-hour HH:MM) for timed kinds, or the amount left for an approaching goal alert. If they didn't say one, or said only "before 9 am", ask them what time; never choose it yourself. At most 20 reminders and 6 notifications a day. It shows in the app under the assistant's name, with Undo.

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": {
      "kind": "<kind>"
    },
    "name": "trainrec_set_reminder"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoLocal time, HH:MM 24-hour, as the person says it. Required for every kind but goal; ask them if they didn't say.
idNoTo change an existing reminder. Leave out to add one.
onNoDefault true. false keeps it but sends nothing.
daysNo1 = Monday to 7 = Sunday. Leave out for every day.
goalNogoal only.
kindYes
mealNolog_food only.
textNocustom only. What it says, up to 80 characters: "Take creatine".
streakNostreak only. training_weeks: weeks in a row with a workout; training_days: days in a row with a workout or food logged.
versionNoRequired with id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare non-read-only, non-destructive, closed-world; the description goes well beyond that by explaining that reminders start at zero, are skipped for the day once the activity is done, that goal alerts are suppressed between 22:00 and 07:00, that recap fires daily, and that the result appears in-app under the assistant's name with Undo — disclosing reversibility and rate-style limits.

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?

Purpose and the add-vs-change distinction are front-loaded, and the kind taxonomy follows logically. It is dense and somewhat run-on in the middle (the kind list crams parenthetical behavior into a single sentence), but nearly every sentence carries operational information rather than filler.

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 10-parameter, nested-object, mutation tool with no output schema, the description covers the kind taxonomy, trigger requirements, hard limits, time-window exclusions, and user-visible outcome. An agent has enough to call it correctly and to know when to stop and ask the user.

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?

Schema coverage is 90%, so the baseline is 3, but the description adds real meaning: it explains each kind's trigger semantics (timed vs. goal-approaching amount left), that the time must come from the person in local 24-hour HH:MM, and that id+version are the change path. It adds context beyond the schema rather than restating it.

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 pair and resource: 'Adds a reminder, or changes one (give its id and version)', and frames the tool in the domain ('TrainRec's notifications on the person's phone'). The upsert framing makes it distinguishable from listing (trainrec_reminders) and deleting (trainrec_delete_reminder) siblings without needing their schemas.

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 explicit when-to-use ('when they ask to be reminded of something, this is how') plus a hard rule not to invent a trigger time and to ask instead. It also states operational limits (20 reminders, 6 notifications a day). It stops short of naming which sibling to use for viewing or removing reminders, so it is clear context without explicit alternatives.

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

All TrainRec toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources