Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

Function order sheet: food quantities for an event (paid, $1)

plan_function_order
Destructive

Calculate catering quantities for an event from guest count and service style, returning grams or pieces per guest, totals, and optional purchase weight and cost per head.

Instructions

Function catering quantities from head chef Cristopher's verified answers. Styles: plated, alternate drop, buffet (1-3 proteins), family-style, canapes, grazing, breakfast buffet, morning tea, afternoon tea, working lunch. Send guests and style; get grams or pieces per guest and totals for protein, sides, salads, dessert, bread and canapes. Add ingredients and price per kg for the weight to buy and cost per head, with workings. Only a 200 answer is charged; refusals and 404s are free.

Use when the user is catering an event and asks how much food to order for N guests. Send guests and style; for canapes give durationHours, or canapesBefore true when they come before a sit-down meal; for buffet give proteinCount (1-3). A field that doesn't go with the style is a free 400. For the weight to buy and cost per head, add buy lines naming an item key from a first answer (protein, protein-1, starch...) and an ingredient check_coverage lists under yieldCost. Pass on notCovered as given: nothing missing is filled in. Costs $1. 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": {
      "guests": "<guests>",
      "style": "<style>"
    },
    "name": "plan_function_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
buyNo
styleYes
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
guestsYes
coursesNo
currencyNoOnly with priced buy lines.
mealTimeNo
alongsideNo
selfServeNo
proteinCountNo
canapesBeforeNo
durationHoursNo
straightFromWorkNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

Discloses far more than the annotations: $1 cost charged only on a 200 answer, 400/404/422 free, automatic USDC payment via x402 with test USDC on base-sepolia, per-session and per-day spend caps, free dryRun that signs nothing, and that notCovered must be passed through unfilled. It also constrains the correctness claim about chef verification by tying it to the result label, which is exactly the kind of caveat an agent needs before relaying output.

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?

Front-loaded with purpose and styles, but there is visible duplication: "Send guests and style" appears twice, and "Only a 200 answer is charged" is restated with the free-status codes. The final chef-verification and refusal paragraphs are load-bearing, yet the middle section mixes payment mechanics into invocation guidance, making the whole longer than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, side-effectful, 13-parameter tool with no output schema, the description covers pricing mechanics, free pre-flight via dryRun, output shape (grams or pieces per guest plus totals), and the paid-vs-free distinction. The remaining hole is the cluster of optional modifiers (selfServe, alongside, mealTime, courses, straightFromWork) that can change results but are never explained.

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?

With only 15% schema description coverage across 13 parameters, the description compensates for the important ones: guests, style, durationHours, canapesBefore, proteinCount, the buy lines with item keys and price per kg, and dryRun. But courses, currency, mealTime, alongside, selfServe, straightFromWork, share and pricePerLb get no explanation anywhere, so several parameters remain guesswork for an agent.

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 (compute catering quantities per guest for an event) and enumerates the ten supported styles, which map directly onto the style enum. It also distinguishes itself from the free sibling by pointing at check_coverage and by telling the agent to add buy lines only when cost per head is wanted.

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?

Gives explicit when-to-use ("when the user is catering an event and asks how much food to order for N guests") plus conditional parameter rules: durationHours for canapes, canapesBefore for pre-meal canapes, proteinCount for buffet. It also warns that a refusal is final and to consult check_coverage when unsure, though it does not contrast against calculate_amount_to_buy or calculate_yield_and_cost, which an agent could easily confuse with this tool.

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