Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

Gluten-free bread answers (paid, $0.01)

get_gluten_free_bread_answer
Destructive

Answer gluten-free bread questions about flour, starter, recipes, techniques, and fixes, including troubleshooting and ingredient swaps; check coverage or dry-run cost before paying.

Instructions

Gluten free sourdough starter, gluten free flour hydration, psyllium substitute and tested GF bread recipes from head chef Cristopher's verified answers. Topics: recipe (ingredient grams, baker's %, timings, oven temperatures), fix (gummy, dense, pale crust), technique (psyllium, proofing, shaping, scoring, steam), flour, starter, swap or compare. Refused: allergen, mould and spoilage questions. Only a 200 answer is charged; refusals and 404s are free.

Pick a topic: flour, starter, technique or recipe with name; swap with name (the ingredient to replace) and optionally use; compare with by (hydration, protein or fermentation); fix with problem (what went wrong, e.g. "gummy crumb"). An unlisted name or problem gets a free 404 with the valid ones (check_coverage section glutenFree lists them). Pass on the answer's glutenFree line and any cautions as given. Allergen, mould, spoilage and storage questions 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": {
      "topic": "<topic>"
    },
    "name": "get_gluten_free_bread_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
byNocompare only, required.
useNoswap only, optional: the replacement you have in mind.
nameNoflour, starter, technique, recipe, swap (the ingredient to replace): required. Not with compare or fix.
topicYes
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
problemNofix only, required: what went wrong, e.g. gummy crumb.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond the annotations, disclosing the $0.01 charge, x402/USDC payment mechanics, per-session and per-day spend caps, which status codes are billed versus free, the free dryRun path, and that a refusal is final. It also warns that 'chef-verified by Cristopher' may only be claimed when the result's label says so, which is exactly the kind of behavioral caveat annotations cannot express. This makes the destructiveHint=true annotation read as monetary risk, not data loss, and the description explains that risk.

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 content is valuable but not front-loaded and is repetitive: billing is restated three times ('Only a 200 answer is charged; refusals and 404s are free' and '...400, 404 and 422 are free') and the $0.01 price appears in the title and twice in the body. A tighter structure would separate purpose, parameter routing, and billing into distinct blocks.

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, multi-topic, conditionally-parameterized tool with no output schema, the description covers cost, billing conditions, refusal categories, validation behavior, dry-run, and the chef-verified caveat, and it hints at return content (the glutenFree line, cautions, result label). The remaining gap is the exact shape of a successful response, which is only lightly sketched.

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 83% schema coverage the baseline is 3, but the description adds real routing logic: which parameter goes with which topic, that name is invalid with compare/fix, and that an unlisted name yields a free 404 listing valid values. That cross-parameter conditional meaning is not in the schema and materially reduces misuse.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it returns chef-written answers on gluten-free bread topics (recipe, fix, technique, flour, starter, swap, compare). An agent can tell what it retrieves and that a sibling, check_coverage, is the prerequisite lookup. It is clear, but the core purpose is buried under pricing and refusal detail rather than stated crisply up front.

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?

Guidance is explicit: pick a topic and pair it with the right parameter (name for flour/starter/technique/recipe/swap, by for compare, problem for fix), call check_coverage first when unsure, and use dryRun for a free quote. What is missing is a direct contrast with get_sample_answer, but the when-to-use, when-not (allergen/mould/spoilage refused) and alternatives are otherwise well covered.

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