Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

Menu price and food cost % for a dish (paid, $0.01)

calculate_menu_price
Destructive

Calculate a dish's plate cost, food cost % and the menu price that hits your target from ingredient lines or a plate cost. Checks ON TARGET, WATCH or OVER TARGET against a 30% goal.

Instructions

Menu price and food cost % for a dish from head chef Cristopher's verified costing rules. Send ingredient lines (qty, pack price, pack size, yield %) or a plate cost, and the menu price; get plate cost with a 3% waste and garnish allowance, food cost % ex GST, ON TARGET, WATCH or OVER TARGET against a 30% target, and the menu price that hits target, rounded up to the next 50 cents, with workings. Target, allowance and tax adjustable. Only a 200 answer is charged; refusals are free.

Use for one dish's plate cost, food cost % and the menu price that hits target. Send lines (each with qty, packPrice and packSize; unit and packUnit both or neither) or plateCost, not both. menuPrice is as shown on the menu, tax included unless pricesIncludeTax is false. Food lines only: staff, labour or money lines are a free 400. For several dishes with units sold, use calculate_menu_engineering instead. 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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "calculate_menu_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
linesNo
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
taxPctNoOnly with pricesIncludeTax true.
roundToNopriceAtTarget is rounded up to the next multiple.
menuPriceNoAs shown on the menu.
plateCostNoA plate cost you already have.
targetPctNo
allowancePctNoWaste and garnish allowance. Not with plateCostIncludesAllowance true.
pricesIncludeTaxNo
plateCostIncludesAllowanceNoWith plateCost only. True when it already has the allowance in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: cost of $0.01, x402 USDC payment with per-session and per-day spend caps, only HTTP 200 billed while 400/404/422 are free, dryRun signing nothing, refusals being final, and the rule to claim 'chef-verified by Cristopher' only when the result label says so. The one gap is that destructiveHint=true is never explained — nothing in the description says what state, if any, is affected — but nothing in the text contradicts it either.

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 the computation and its outputs, then the input rules, then the payment mechanics — a sensible order for an agent. It loses a little to duplication: 'Only a 200 answer is charged' appears twice, and the $0.01 price is repeated from the title and again at the end.

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 10-parameter paid tool with no output schema, the description supplies what an agent needs: the exact return contents (plate cost, food cost % ex GST, ON TARGET/WATCH/OVER TARGET verdict, priceAtTarget, workings), the input exclusivity rules, and the billing/refusal semantics. Nothing material to a correct call 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?

Adds meaning the 70%-covered schema does not: unit and packUnit must be supplied together or omitted, menuPrice is tax-inclusive unless pricesIncludeTax is false, allowancePct does not apply with plateCostIncludesAllowance, and the defaults (30% target, 3% allowance, 50-cent rounding) are stated. Some parameters, notably targetPct and roundTo mechanics, are left largely to their schema descriptions.

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 and resource: plate cost, food cost % and target-hitting menu price for one dish, sourced from 'head chef Cristopher's verified costing rules'. It explicitly carves out the sibling boundary ('For several dishes with units sold, use calculate_menu_engineering instead'), so an agent can route without opening either 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 (one dish), when-not (several dishes with units sold → calculate_menu_engineering), input exclusivity ('lines ... or plateCost, not both'), and an escalation path ('If unsure what is covered, call check_coverage first (free)'). It also tells the agent to try dryRun first for a free quote, which is a concrete pre-flight rule.

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