Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

Menu engineering from sales (paid, $0.02)

calculate_menu_engineering
Destructive

Classifies each menu dish as Star, Plowhorse, Puzzle or Dog from POS units sold, menu price and plate cost, adding contribution margin, menu mix and food cost with an action.

Instructions

Menu engineering from POS sales with head chef Cristopher's verified costing rules. Send 2-200 dishes with units sold, menu price (inc GST by default) and plate cost; each dish gets contribution margin, menu mix %, food cost % and its class: Star, Plowhorse, Puzzle or Dog (70% popularity rule, sales-weighted average margin), with his action for each. The whole menu is one pool; catering platters are judged on their own. Only a 200 answer is charged; refusals are free.

Use when the user has units sold per dish for a period (one week from the POS is enough) and wants each dish classed. Send 2-200 dishes, each with name, unitsSold, menuPrice (as shown on the menu) and plateCost; mark catering platters with catering true. For one dish's price, use calculate_menu_price instead. Pass on each dish's action as given. Costs $0.02. 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": {
      "dishes": "<dishes>"
    },
    "name": "calculate_menu_engineering"
  }
}

Input Schema

NameRequiredDescriptionDefault
dishesYes
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
taxPctNoOnly with pricesIncludeTax true.
pricesIncludeTaxNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description goes well past them by disclosing paid-operation mechanics: $0.02 per call, USDC via x402 with base-sepolia test USDC, per-session and per-day spend caps, charge only on 200 with 400/404/422 free, and dryRun signing nothing. It also adds an unusual honesty constraint about only claiming 'chef-verified by Cristopher' when the result label says so, which no annotation conveys.

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

Conciseness3/5

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

The key constraint (units sold per dish, 2-200 dishes, $0.02) is front-loaded, but the text repeats itself: '2-200 dishes' appears twice, and the 200-only charging rule is stated twice with overlapping enumerations ('refusals are free' vs. '400, 404 and 422 are free'). The chef-verified caveat and refusal-finality note are useful but add length that could be tightened.

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, mutating-billed calculator with no output schema, the description compensates by describing the return payload field-by-field and covering billing, quoting, and eligibility. An agent can decide, call, and report results correctly without further documentation.

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?

With only 50% schema description coverage, the description carries real weight: it clarifies that menuPrice is 'as shown on the menu' and inclusive of GST by default, that unitsSold is per-dish for a period, and that catering platters must be marked with catering true and are pooled separately. It leaves pricesIncludeTax and taxPct's default interaction underspecified, so the GST toggle still requires inference from 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?

The description states a specific verb (menu engineering) on a specific input (POS units sold) and enumerates the exact outputs returned per dish: contribution margin, menu mix %, food cost %, and a Star/Plowhorse/Puzzle/Dog class using a named 70% popularity rule with sales-weighted average margin. It also explicitly excludes the sibling case: 'For one dish's price, use calculate_menu_price instead.'

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?

It gives a concrete trigger ('user has units sold per dish for a period (one week from the POS is enough)'), names the sibling to use instead for pricing questions, explains dryRun for a free quote, and points to check_coverage when scope is unclear. It even prescribes downstream behavior: pass on each dish's action as given, and treat a refusal as final rather than rephrasing.

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