Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

How much to buy for N portions (paid, $0.01)

calculate_amount_to_buy
Destructive

Calculate how much of an ingredient to buy for a target number of portions and serving size, with rounded-up purchase weights and optional cost and food-cost percentages.

Instructions

How much to buy: e.g. how much brisket for 120 people at 180 g cooked each. Send ingredient, portions and portion size (g, kg, lb, oz); get the weight to buy (best/mid/worst, rounded up) from head chef Cristopher's verified trim and cook-loss ranges. Add price per kg/lb and menu price ex GST/VAT for total cost, cost per portion and that ingredient's food cost %, with workings. Refused, never guessed: allergen, curing and preserving terms. Only a 200 answer is charged; refusals and 404s are free.

Use when the user starts from portions ("120 people, 180 g cooked each"). For "I bought 5 kg, what do I get", use calculate_yield_and_cost instead. portionSize is one portion as served (cooked when basis is cooked). For cost, give pricePerKg or pricePerLb (the price as bought; not both, and not "price"). sellPrice is the ex-tax menu price of one portion and needs one of them. currency is required: the user's 3-letter currency code (display only). 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": {
      "ingredient": "<ingredient>",
      "portions": "<portions>",
      "portionSize": "<portionSize>",
      "currency": "<currency>"
    },
    "name": "calculate_amount_to_buy"
  }
}

Input Schema

NameRequiredDescriptionDefault
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
currencyYesThe user's 3-letter currency code, e.g. AUD, USD, GBP. Display only.
portionsYesHow many portions to buy for.
sellPriceNoMenu price of one portion, excluding GST/VAT/sales tax. Needs pricePerKg or pricePerLb (400 without).
ingredientYes
pricePerKgNoPrice per kg as bought. Not with pricePerLb.
pricePerLbNoPrice per lb as bought. Not with pricePerKg.
portionSizeYesWeight of one portion as served — cooked when the chef has a cook-loss range for the ingredient, otherwise trimmed raw (the response's `basis` says which). portions × portionSize is at most 10 t.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Adds behavior far beyond the annotations: exact price ($0.01), which HTTP outcomes are billed (only 200; 400/404/422 free), x402 USDC payment including the base-sepolia test-USDC condition, per-session and per-day spend caps, and that dryRun signs nothing. It also discloses refusal semantics (allergen/curing/preserving refused, never guessed) and a labeling constraint ('chef-verified' only when the result label says so), which the destructiveHint=true annotation alone cannot convey.

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-loads purpose and a concrete example before rules, then groups cost-parameter rules, payment terms, and refusal policy. Almost every sentence carries new information, though the billing rule is stated twice ('Only a 200 answer is charged; refusals and 404s are free' then '400, 404 and 422 are free'), a minor redundancy in an otherwise dense 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?

For a paid, non-idempotent, open-world tool with 8 parameters, a nested object, and no output schema, the definition covers everything an agent needs: payment mechanics and caps, free-vs-charged outcomes, dry-run quoting, the cooked-vs-raw basis of results, guidance to check coverage first, and how to report verification status. Nothing material for correct invocation is missing.

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 88%, so the baseline is 3, but the description adds real meaning: portionSize is one portion as served and is cooked when basis is cooked, pricePerKg vs pricePerLb are mutually exclusive and not the same as a 'price' field, sellPrice requires one of them (400 otherwise), and currency is display-only. Only the nested qty/unit constraints are left entirely to 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 computation ('how much to buy for N portions') with a concrete worked example ('how much brisket for 120 people at 180 g cooked each') and states exactly what comes back (weight to buy at best/mid/worst, rounded up, plus cost and food cost %). It explicitly positions itself against the inverse sibling calculate_yield_and_cost, so an agent can route 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?

Gives explicit when-to-use ('user starts from portions') and when-not-to ('For "I bought 5 kg, what do I get", use calculate_yield_and_cost instead'), plus escalation to check_coverage when coverage is unclear and dryRun for a free quote. Exclusions and alternatives are both named, with no inference required.

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