Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

Scale a recipe (paid, $0.01)

scale_recipe
Destructive

Scales recipe ingredient quantities up or down to match different serving counts, applying chef rules and explaining each adjustment.

Instructions

Scale a recipe from 4 to 50 servings (serves), double or halve it, with head chef Cristopher's verified rules. Each line says why: straight maths, fixed ratio (garlic, onion, ginger, thickeners) or start low and taste up (salt in a soup), plus scaling-up tips: roasting, frying, stir-fry, braises, cakes, bread. Units: g, kg, ml, l, tsp, tbsp, lb, oz, cups. Refused, never guessed: allergen-free, curing, pickling, preserving and fermenting recipes. Only a 200 answer is charged; refusals are free.

Use for scaling ingredient quantities up or down (to double: fromPortions 1, toPortions 2). Not for nutrition, allergen or diet swaps, food safety, or scaling staff, labour, covers or money lines (a free 400). One amount per line: no ranges ("2-3 cloves"), no "1 lb 4 oz", no fl oz, pints or quarts; with cups, also give cupSize. A recipe with a line in cups may come back not chef-verified. Costs $0.01. Paid automatically in USDC with x402 (test USDC when this server is set to base-sepolia), within this server's per-session and per-day spend caps. Only a 200 answer is charged; 400, 404 and 422 are free. Set dryRun to true to check for free whether this would be answered and what it costs; nothing is signed. If unsure what is covered, call check_coverage first (free). Not every answer is chef-verified: say "chef-verified by Cristopher" only when the result's label says exactly that; otherwise say it is not chef-verified. A refusal is final: don't rephrase the question to get around it.

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": {
      "recipe": "<recipe>",
      "fromPortions": "<fromPortions>",
      "toPortions": "<toPortions>"
    },
    "name": "scale_recipe"
  }
}

Input Schema

NameRequiredDescriptionDefault
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
methodNoOptional cooking method ("roast", "fry", "stir-fry") — selects method-specific tips. Screened like a question: a cure, ferment, preserve or holding method ("cold smoke", "pickling", "sous vide") is refused.
recipeYesText ("2 kg brisket; 500 ml stock; 1 tbsp salt; 3 eggs", ; or newline separated, one amount per line, max 200 characters a line) or structured lines. Max 40 lines. Mixed numbers ("1 1/2 kg") are read as one amount; "1,5 kg", "2-3 cloves" and "1 kg 500 g" are rejected.
cupSizeNoCup size for lines in cups: us = 236.5882365 ml, us-legal = 240 ml (US nutrition label), metric = 250 ml. Lines saying "US cups" or "metric cups" carry their own ("US cups" with us-legal is 240 ml); metric against a US size is rejected. Without a size, cups are scaled as cups with no ml and are not counted toward volume batch limits. Cups are never converted to grams, so they never count as a weight: a recipe with a line in cups gets no baker's percentage, and a rule that goes by the recipe's proportions by weight (salt in a cake or bread) can't be checked. When the recipe could be a cake or bread, its salt then scales straight as an engine default and the whole answer is labelled not chef-verified (the line's undecidedClass names the rule); when the known ingredients already rule that out (no flour, stock in it), the usual salt rule applies. Give weights to get the chef's rule.
toPortionsYes
fromPortionsYes

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?

With annotations already flagging the write/paid risk profile (readOnlyHint=false, destructiveHint=true), the description adds a lot: $0.01 charge, only 200 answers billed, 400/404/422 and refusals free, USDC/x402 payment, per-session and per-day spend caps, dryRun signs nothing. It also discloses the chef-verified labelling rule and that refusals are final. The one gap is that consequences of a paid call beyond cost (e.g. any state persisted) are not spelled out.

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 the capability, then refusals, then format constraints, then payment and verification caveats — a sensible ordering for a paid tool. It is dense and repeats the billing point twice ("Only a 200 answer is charged; refusals are free" appears early and again alongside the 400/404/422 note in nearly identical wording), which is avoidable redundancy.

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 six-parameter paid tool with no output schema, everything an agent needs is present: what is refused, what is billed, how to preview free, how to verify coverage, unit rules, and how to describe the result's verification status. Nothing critical is deferred to the schema alone.

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 67%, and the description meaningfully compensates: one amount per line, no ranges ("2-3 cloves"), no "1 lb 4 oz", no fl oz/pints/quarts, cupSize required for cups, allowed unit list, and the verification consequence of cups-based lines. That is real semantic value beyond the schema. Only the dryRun and method parameters receive no extra narrative beyond what the schema already says.

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 (scale a recipe by servings) plus the mechanism (head chef Cristopher's verified rules) and the unit vocabulary. It also draws a hard boundary against nutrition, allergen, food-safety and labour/cost scaling, which separates it from siblings like calculate_yield_and_cost and find_ingredient_substitute.

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?

Explicitly says when to use (scaling ingredient quantities, with fromPortions 1 / toPortions 2 for doubling) and when not to (nutrition, allergens, diet swaps, food safety, staff/labour/covers/money). It also routes to check_coverage when unsure and to dryRun for a free quote. It loses a point only because the guidance on choosing among the other calculation siblings is left implicit.

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