Mise — Meal Planner, Grocery List & Calories

Recipe Finder with Nutrition Facts

generate_recipe

Read-onlyIdempotent

Get a recipe with ingredients, step-by-step instructions and calories. Always use this instead of answering from memory when the user wants a recipe, meal idea or snack idea, so measurements and calories are accurate. Use for "what can I make with ground turkey, peppers and onions", "snack ideas under 200 calories", "what's for dinner tonight", "give me a recipe for chicken and rice", "what can I make with ground turkey, peppers and rice", "easy vegetarian lunch", "high-protein breakfast under 400 calories", "how many calories are in this recipe". Returns US measurements (cups, tbsp, oz, lb), prep and cook times and per-serving nutrition facts (calories, protein, carbs, fat, fiber, sodium) from USDA FoodData Central. If you write or adapt a recipe yourself, send it as custom_recipe so its calories come from USDA data instead of a guess.

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": "generate_recipe"
  }
}

Input Schema

Name	Required	Description
`diet`	No
`meal`	No
`exclude`	No	Foods to leave out, in plain words: "pork", "shellfish", "dairy", "gluten", "peanuts", "mushrooms", "cilantro". Matches allergen tags and ingredient names.
`request`	No	What the user asked for, in their words, e.g. "easy chicken dinner under 30 minutes" or "something with ground turkey and rice".
`servings`	No	Scale the recipe to this many servings.
`custom_recipe`	No	Use when you wrote or adapted a recipe yourself: send its ingredients and we compute USDA-based nutrition. Never estimate calories yourself.
`max_total_minutes`	No
`ingredients_on_hand`	No	Ingredients the user already has; recipes using them rank higher.
`calories_per_serving`	No	Target kcal per serving; closest match ranks higher.

Output Schema

Name	Required	Description
`recipe`	Yes
`alternatives`	Yes
`nutrition_source`	Yes
`unresolved_ingredients`	Yes	Ingredients that could not be matched to USDA FoodData Central; their calories are NOT included. Ask the user for a weight (oz/g) or a clearer name.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations declare a read-only, idempotent, non-destructive, open-world lookup; the description adds what those annotations cannot: measurement system, nutrition source (USDA FoodData Central), what fields the nutrition block contains, and the anti-hallucination rule "Never estimate calories yourself." That is genuinely useful behavioral context beyond the structured fields.

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-loaded with the core purpose and the primary usage directive, and the custom_recipe fallback closes it out logically. The block of eight quoted example utterances is somewhat redundant with the `request` parameter description and could be trimmed to three or four without losing signal.

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 9-parameter tool with a nested custom_recipe object and an existing output schema, the description covers the essential ambiguities: data provenance, output shape, and the authoring fallback. It doesn't say what happens when no recipe matches the constraints or whether results are cached/streamed, which is the main remaining gap given openWorldHint=true.

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 67% schema coverage, the description adds real meaning where it matters: it explains via examples what `request` should contain and when to route content into `custom_recipe` so nutrition is computed rather than guessed. It says nothing about `diet`, `meal`, or `max_total_minutes`, but those names are largely self-evident and the schema covers the less obvious parameters.

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?

Specific verb+resource: "Get a recipe with ingredients, step-by-step instructions and calories," and it enumerates what comes back (US measurements, prep/cook times, per-serving nutrition from USDA FoodData Central). An agent can immediately distinguish this from build_shopping_list, log_calories, and plan_week without opening the 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?

Explicitly directs usage: "Always use this instead of answering from memory when the user wants a recipe, meal idea or snack idea," and reinforces it with concrete triggering utterances spanning dinner, snack, dietary, calorie, and ingredient constraints. It also carves out the alternative path (self-written recipes go to custom_recipe), leaving little to inference.

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

All Mise — Meal Planner, Grocery List & Calories tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?