Skip to main content
Glama

Scale recipe

scale_recipe
Read-onlyIdempotent

Scale every ingredient in a recipe from one serving count to another (0.1x to 20x), with kitchen-friendly fraction hints; items without a quantity pass through unchanged. Use when cooking for more or fewer people. Do NOT use to change units (use convert_units) or to combine several recipes' ingredients (use merge_shopping_list).

Input Schema

NameRequiredDescriptionDefault
ingredientsYesRecipe ingredients, e.g. [{"item":"flour","quantity":2,"unit":"cup"},{"item":"salt","note":"to taste"}]
to_servingsYesServings wanted, positive; to_servings / from_servings must be 0.1-20, e.g. 10
from_servingsYesServings the recipe is written for, positive, e.g. 4

Output Schema

NameRequiredDescriptionDefault
noteYesExplanation of the scaling applied
factorYesScaling factor to_servings / from_servings (4 significant digits)
ingredientsYesScaled ingredients, in input order
to_servingsYesServings scaled to
from_servingsYesServings the recipe was written for

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed24 schema fields changed
    • changedInput schema / properties / from_servings / description
      Previous value: -"Servings the recipe is written for"New value: +"Servings the recipe is written for, positive, e.g. 4"
    • addedInput schema / properties / from_servings / exclusiveMinimum
      Added value: +0
    • changedInput schema / properties / ingredients / description
      Previous value: -"Ingredients with optional quantity and unit"New value: +"Recipe ingredients, e.g. [{\"item\":\"flour\",\"quantity\":2,\"unit\":\"cup\"},{\"item\":\"salt\",\"note\":\"to taste\"}]"
    • changedInput schema / properties / ingredients / items / properties / note / description
      Previous value: -"Preparation note kept as-is, e.g. 'to taste'"New value: +"Text shown instead of an amount when quantity is omitted, e.g. 'to taste' (default 'as needed')"
    • changedInput schema / properties / ingredients / items / properties / quantity / description
      Previous value: -"Amount; omit it for items like 'salt to taste'"New value: +"Amount, non-negative; omit for items like 'salt to taste'"
    • addedInput schema / properties / ingredients / items / properties / quantity / minimum
      Added value: +0
    • changedInput schema / properties / ingredients / items / properties / unit / description
      Previous value: -"Unit such as cup, tbsp, g or a count label like 'clove'"New value: +"Unit such as cup, tbsp, g, or a free count label like 'clove' or 'egg'"
    • addedInput schema / properties / ingredients / minItems
      Added value: +1
    • changedInput schema / properties / to_servings / description
      Previous value: -"Servings you want"New value: +"Servings wanted, positive; to_servings / from_servings must be 0.1-20, e.g. 10"
    • addedInput schema / properties / to_servings / exclusiveMinimum
      Added value: +0
    • addedOutput schema / properties / factor
      Added value: +{
      +  "description": "Scaling factor to_servings / from_servings (4 significant digits)",
      +  "type": "number"
      +}
    • addedOutput schema / properties / from_servings
      Added value: +{
      +  "description": "Servings the recipe was written for",
      +  "type": "number"
      +}
    • changedOutput schema / properties / ingredients / description
      Previous value: -"List of scaled ingredients"New value: +"Scaled ingredients, in input order"
    • removedOutput schema / properties / ingredients / items / properties / note
      Removed value: -{
      -  "description": "Preparation note kept as-is, e.g. 'to taste'",
      -  "type": "string"
      -}
    • addedOutput schema / properties / ingredients / items / properties / original
      Added value: +{
      +  "description": "Original amount as text, or the pass-through note",
      +  "type": "string"
      +}
    • removedOutput schema / properties / ingredients / items / properties / quantity
      Removed value: -{
      -  "description": "Scaled amount; omitted for items like 'salt to taste'",
      -  "type": "number"
      -}
    • addedOutput schema / properties / ingredients / items / properties / scaled
      Added value: +{
      +  "description": "Scaled quantity (2 decimals); null when no quantity was given",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / ingredients / items / properties / scaled_display
      Added value: +{
      +  "description": "Scaled amount with unit and fraction hint, e.g. '2 1/2 cups (2.5)'",
      +  "type": "string"
      +}
    • addedOutput schema / properties / ingredients / items / properties / scaled_flag
      Added value: +{
      +  "description": "true when the ingredient was scaled, false when passed through",
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / ingredients / items / properties / unit
      Removed value: -{
      -  "description": "Unit such as cup, tbsp, g or a count label like 'clove'",
      -  "type": "string"
      -}
    • changedOutput schema / properties / ingredients / items / required
      Previous value: -[
      -  "item"
      -]New value: +[
      +  "item",
      +  "original",
      +  "scaled",
      +  "scaled_display",
      +  "scaled_flag"
      +]
    • addedOutput schema / properties / note
      Added value: +{
      +  "description": "Explanation of the scaling applied",
      +  "type": "string"
      +}
    • addedOutput schema / properties / to_servings
      Added value: +{
      +  "description": "Servings scaled to",
      +  "type": "number"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "ingredients"
      -]New value: +[
      +  "from_servings",
      +  "to_servings",
      +  "factor",
      +  "ingredients",
      +  "note"
      +]
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "ingredients": {
      +      "description": "List of scaled ingredients",
      +      "items": {
      +        "properties": {
      +          "item": {
      +            "description": "Ingredient name",
      +            "type": "string"
      +          },
      +          "note": {
      +            "description": "Preparation note kept as-is, e.g. 'to taste'",
      +            "type": "string"
      +          },
      +          "quantity": {
      +            "description": "Scaled amount; omitted for items like 'salt to taste'",
      +            "type": "number"
      +          },
      +          "unit": {
      +            "description": "Unit such as cup, tbsp, g or a count label like 'clove'",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "item"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "ingredients"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral detail beyond them: the 0.1x–20x scaling envelope, that output includes kitchen-friendly fraction hints, and that items lacking a quantity pass through unchanged. It stops short of describing ordering or rounding precision, so it is strong but not exhaustive.

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

Conciseness5/5

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

Three sentences, zero padding: purpose and bounds first, usage context second, routing exclusions last. Each sentence carries decision-relevant information.

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 pure read/transform tool with full annotation coverage, a 100%-documented schema, and an output schema that handles return values, the description supplies everything left: bounds, pass-through behavior, and sibling routing. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so the baseline is 3. The description's ratio-bound statement (0.1x to 20x) duplicates what the to_servings schema already documents, and it adds no interpretation for the nested ingredient fields (item/note/unit/quantity). Credit-worthy but not additive over 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?

Names a specific verb (scale) and resource (every ingredient in a recipe) plus the exact scope (serving count change, 0.1x–20x). It also states the pass-through edge case and names the two siblings it must not be confused with, so an agent can identify it without opening a 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 positive trigger ("Use when cooking for more or fewer people") and two explicit exclusions with named alternatives: unit changes go to convert_units, ingredient combining goes to merge_shopping_list. Nothing is left to inference.

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