Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

What to use instead (paid, $0.01)

find_ingredient_substitute
Destructive

Find cooking ingredient substitutes with amounts and context, including swaps to avoid. Ask what to use instead and get a yes, no, or depends verdict.

Instructions

What can I use instead of buttermilk, creme fraiche, mascarpone, mirin or gelatine leaves? Get head chef Cristopher's verified swaps: yes, no or depends (and on what), with amount and context, including swaps not to make. Over 40 ingredients, also butter, cream, sugars, honey, flours, fresh yeast, white wine, beef stock, soy sauce, shallots. Refused, never guessed: allergens and dairy-, egg- or gluten-free swaps, storage, preserving. Only a 200 answer is charged; refusals and 404s are free.

ingredient is what the user wants to replace. use is optional: the replacement they have in mind, to get just that answer. A "no" verdict is advice too: pass it on, with what it depends on for "depends". Allergy, dairy-, egg- or gluten-free and storage framings are refused (free 422). 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>"
    },
    "name": "find_ingredient_substitute"
  }
}

Input Schema

NameRequiredDescriptionDefault
useNoOptional: the replacement you have in mind.
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
ingredientYesWhat you want to replace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare hints (destructiveHint=true, openWorldHint=true, idempotentHint=false); the description adds the actual cost mechanism — $0.01 charged only on a 200, 400/404/422 free, paid in USDC via x402 under per-session and per-day caps, with dryRun signing nothing. It also discloses an output caveat not in any schema (only label chef-verified by Cristopher when the result says so). Slightly reduced for repeating the charging rule twice and not clarifying why destructiveHint is true (spend vs. data change).

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?

Purpose is front-loaded, but the paragraph is dense and repetitive — the charge rule ("Only a 200 answer is charged") appears twice, along with $0.01 restated in the title, body and later sentence. Payment, refusal, dryRun and chef-verified caveats are interleaved rather than grouped, making it longer than needed.

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?

There is no output schema, so the description must describe returns, and it does: verdicts of yes/no/depends with amount and context, including swaps not to make, plus the chef-verified label caveat. Payment, refusal and quote mechanics are all covered for a paid, open-world query tool.

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 100%, so baseline is 3, but the description adds meaning beyond it: it clarifies that "use" restricts the answer to just that swap, and that ingredient is what the user wants to replace. dryRun's free, nothing-signed behavior is reinforced beyond the schema's field description.

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 concrete verb and resource — "Get head chef Cristopher's verified swaps" for a named ingredient, returning yes/no/depends verdicts with amount and context. It also scopes the coverage domain (over 40 ingredients, listed examples) and names the sibling check_coverage for boundary cases, so an agent can distinguish it from the other tools.

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 explicit when-not guidance: allergen, dairy-, egg- or gluten-free and storage framings are refused (free 422), and it tells the agent not to rephrase around a refusal. It also routes to alternatives — dryRun=true for a free quote, check_coverage first when unsure, and passing on a "no" verdict as advice.

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