Skip to main content
Glama

joiva_log_drink

Log a drink the signed-in user had from Joiva's drink templates: coffee, tea, milk, cocoa, orange juice, apple spritzer, cola, cola zero, beer or white wine; coffee and tea optionally with milk, oat drink, coffee cream, sugar or butter. Writes food-log entries (the drink plus one row per addition, linked as one drink) with caffeine and alcohol from a cited source, energy and nutrients. Drinks are listed in ml under 'Getrunken', never as a meal. Drinks and additions over 50 kcal end a fast like any food (fasting automation, 50 kcal rule). Its water counts towards the day's hydration target. Plain and sparkling water are not logged here; a drink without a template here is logged like food. Time defaults to now.

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": {
      "drink": "<drink>"
    },
    "name": "joiva_log_drink"
  }
}

Input Schema

NameRequiredDescriptionDefault
mlNoAmount in millilitres; defaults to the usual size
drinkYesWhich drink: 'kaffee' (200 ml), 'espresso' (40 ml), 'schwarztee', 'gruentee', 'kraeutertee' (250 ml each), 'entkoffeiniert' (decaf coffee, 200 ml), 'milch' (a glass of whole milk, 200 ml), 'kakao' (cocoa, 250 ml), 'orangensaft' (orange juice, 200 ml), 'apfelschorle' (apple spritzer, 330 ml), 'cola' (330 ml), 'cola_zero' (330 ml), 'bier' (beer, 500 ml), 'weisswein' (white wine, 150 ml). Drinks over 50 kcal end a fast like any food.
loggedAtNoISO 8601 timestamp with offset, defaults to now
additionsNoAdditions: 'milch' (30 g), 'haferdrink' (30 g), 'sahne' (coffee cream, 15 g), 'zucker' (5 g), 'butter' (10 g). None when black.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / drink / description
      Previous value: -"Which drink: 'kaffee' (200 ml), 'espresso' (40 ml), 'schwarztee', 'gruentee', 'kraeutertee' (250 ml each), 'entkoffeiniert' (decaf coffee, 200 ml), 'milch' (a glass of whole milk, 200 ml; ends a fast like any food over 50 kcal)"New value: +"Which drink: 'kaffee' (200 ml), 'espresso' (40 ml), 'schwarztee', 'gruentee', 'kraeutertee' (250 ml each), 'entkoffeiniert' (decaf coffee, 200 ml), 'milch' (a glass of whole milk, 200 ml), 'kakao' (cocoa, 250 ml), 'orangensaft' (orange juice, 200 ml), 'apfelschorle' (apple spritzer, 330 ml), 'cola' (330 ml), 'cola_zero' (330 ml), 'bier' (beer, 500 ml), 'weisswein' (white wine, 150 ml). Drinks over 50 kcal end a fast like any food."
    • changedInput schema / properties / drink / enum
      Previous value: -[
      -  "kaffee",
      -  "espresso",
      -  "schwarztee",
      -  "gruentee",
      -  "kraeutertee",
      -  "entkoffeiniert",
      -  "milch"
      -]New value: +[
      +  "kaffee",
      +  "espresso",
      +  "schwarztee",
      +  "gruentee",
      +  "kraeutertee",
      +  "entkoffeiniert",
      +  "milch",
      +  "kakao",
      +  "orangensaft",
      +  "apfelschorle",
      +  "cola",
      +  "cola_zero",
      +  "bier",
      +  "weisswein"
      +]
  2. 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 the generic write profile (readOnly=false, destructive=false, non-idempotent); the description adds substantial behavior beyond that: it writes the drink plus one row per addition linked as a single drink, records caffeine/alcohol from a cited source plus energy and nutrients, files under 'Getrunken' in ml rather than as a meal, counts toward hydration, and ends a fast via the 50 kcal rule.

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 is front-loaded in the first clause and nearly every sentence carries new information. It is a dense run-on block, though, and the 50 kcal fasting rule plus the "time defaults to now" fact are stated twice (also in the schema), which is minor waste.

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?

With no output schema and a simple 4-parameter surface, the description covers everything an agent needs: what is written, how portions default, how additions are stored, where it appears in the day view, and the fasting/hydration side effects.

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 description coverage is 100%, so a 3 is the baseline, but the description adds real meaning on top: it clarifies that additions are only meaningful for coffee and tea ("coffee and tea optionally with milk, oat drink, coffee cream, sugar or butter") and that ml/omit falls back to the template's usual size.

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 ("Log a drink") and immediately scopes it to Joiva's drink templates, enumerating them. An agent can distinguish this from joiva_log_food and joiva_log_water 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 clear negative routing: plain and sparkling water are not logged here, and a drink without a template is logged like food — which points at joiva_log_water and joiva_log_food. It stops short of naming those sibling tools explicitly, so the agent must map the categories itself.

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