Skip to main content
Glama

supplemental.pl — EU/PL food law

Calculate a nutrition declaration (Nutrimetr)

nutrition_calc
Read-onlyIdempotent

Deterministic nutrition calculation for a recipe (no AI): energy and nutrients per 100 g, micronutrients with %NRV, candidate nutrition claims (withheld if any ingredient is unresolved), allergens and QUID hints. Ingredient lines with mass or volume and the ingredient name in Polish (the food table matches Polish names only; translate other languages first), e.g. "mąka owsiana 500 g", "mleko 200 ml", "miód 50 g". Usage limit: 20 calculations per user per day (500 for shared Google network addresses). Example: ingredients ["mleko 200 ml"] or ["mąka owsiana 500 g", "mleko 200 ml", "miód 50 g"].

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "lang": "en",
      "ingredients": [
        "mleko 200 ml"
      ],
      "product_form": "solid",
      "product_name": "owsianka"
    },
    "name": "nutrition_calc"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoResponse language. Default: en.
ingredientsYesOne ingredient per item: Polish ingredient name, quantity and unit (g, kg, mg, ml, l), e.g. "mleko 200 ml".
product_formNoDefault solid.
product_nameNoOptional product/recipe label shown in the result (max 120 chars).
mass_loss_pctNoMass loss during processing (e.g. baking), %.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "ingredients": [
      +      "mleko 200 ml"
      +    ],
      +    "lang": "en",
      +    "product_form": "solid",
      +    "product_name": "owsianka"
      +  }
      +]
    • addedInput schema / properties / ingredients / examples
      Added value: +[
      +  [
      +    "mleko 200 ml"
      +  ],
      +  [
      +    "mąka owsiana 500 g",
      +    "mleko 200 ml",
      +    "miód 50 g"
      +  ]
      +]
    • addedInput schema / properties / lang / examples
      Added value: +[
      +  "en",
      +  "pl"
      +]
    • addedInput schema / properties / product_form / examples
      Added value: +[
      +  "solid"
      +]
    • addedInput schema / properties / product_name / examples
      Added value: +[
      +  "owsianka"
      +]
  2. Changed1 schema field changed
    • addedInput schema / properties / product_name / description
      Added value: +"Optional product/recipe label shown in the result (max 120 chars)."
  3. Changed1 schema field changed
    • changedInput schema / properties / ingredients / description
      Previous value: -"One ingredient per item, with quantity and unit (g, kg, mg, ml, l)."New value: +"One ingredient per item: Polish ingredient name, quantity and unit (g, kg, mg, ml, l), e.g. \"mleko 200 ml\"."
  4. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/closed-world/non-destructive, and the description adds substantial behavior beyond them: it is deterministic (no AI), claims are withheld when any ingredient is unresolved, and per-user/per-network rate limits are stated. The unresolved-ingredient caveat is exactly the kind of failure-mode disclosure that prevents misreading partial results.

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?

Front-loaded with purpose and outputs, then input format, then limits and examples – a sensible ordering with no filler sentences. Slight redundancy from repeating example ingredient lists that already appear in the schema's examples block.

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?

There is no output schema, and the description covers the return content well (per-100 g nutrients, %NRV micronutrients, claims, allergens, QUID hints) plus the conditional withholding of claims. Combined with the rate limit and input-format rules, an agent has everything needed to call it and interpret results.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3; the description reinforces the ingredients parameter (Polish-only matching, g/kg/mg/ml/l units) and adds the useful rationale that the food table matches Polish names, which the schema does not explain. However it says nothing about mass_loss_pct or product_form, so it does not exceed the schema on most parameters.

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 ('Deterministic nutrition calculation for a recipe') and enumerates the outputs: energy/nutrients per 100 g, micronutrients with %NRV, candidate claims, allergens, QUID hints. An agent can immediately distinguish this calculation tool from the claim/article lookup siblings.

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 concrete usage conditions: ingredient lines must carry mass or volume, names must be Polish (translate other languages first), with three worked examples and explicit rate limits (20/user/day, 500 for shared Google addresses). It never names an alternative tool or an exclusion case, so it falls short of a 5.

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