Skip to main content
Glama
Tandoor Recipes MCP

Tandoor Recipes MCP

Search recipes

search_recipes
Read-onlyIdempotent

Search recipes by food, keyword, or book names in one request, then filter by rating, cook history, on-hand ingredients, exclusions, and pagination.

Instructions

High-level recipe search. Accepts food/keyword/book names (not IDs) and resolves them internally, typically collapsing 3-4 round-trips into 1. Example: {foods: ["chicken", "broccoli"], exclude_foods: ["peanuts"], keywords: ["weeknight"]}. For complex ID-based filtering, fall back to list_recipes.

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": "search_recipes"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, starting at 1.
booksNoRecipe book names; recipe must be in ANY of these
foodsNoFood names the recipe must contain ALL of
queryNoFuzzy match against recipe names
formatNoResponse detail level. Default "slim".
randomNoReturn results in random order.
makenowNoOnly recipes makeable with currently on-hand foods
keywordsNoKeyword names; recipe must have ANY of these
page_sizeNoResults per page. Default 25, max 100.
rating_gteNoMinimum rating.
rating_lteNoMaximum rating.
sort_orderNoscore | -score | name | -name | lastcooked | -lastcooked | rating | -rating | times_cooked | -times_cooked
exclude_foodsNoFood names the recipe must NOT contain any of
timescooked_gteNoMinimum number of times cooked.
timescooked_lteNoMaximum number of times cooked.
exclude_keywordsNoKeyword names to exclude

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv3.4.4
    • changedInput schema / properties / books / description
      Previous value: -"Recipe book names — recipe must be in ANY of these"New value: +"Recipe book names; recipe must be in ANY of these"
    • changedInput schema / properties / keywords / description
      Previous value: -"Keyword names — recipe must have ANY of these"New value: +"Keyword names; recipe must have ANY of these"
    • addedInput schema / properties / page / description
      Added value: +"Page number, starting at 1."
    • addedInput schema / properties / page_size / description
      Added value: +"Results per page. Default 25, max 100."
    • addedInput schema / properties / random / description
      Added value: +"Return results in random order."
    • addedInput schema / properties / rating_gte / description
      Added value: +"Minimum rating."
    • addedInput schema / properties / rating_lte / description
      Added value: +"Maximum rating."
    • addedInput schema / properties / timescooked_gte / description
      Added value: +"Minimum number of times cooked."
    • addedInput schema / properties / timescooked_lte / description
      Added value: +"Maximum number of times cooked."
  2. First observedv3.4.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds real context beyond that: name resolution happens internally and it typically collapses 3-4 round-trips into 1, which tells the agent why to prefer this tool.

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?

Three short sentences, front-loaded with the purpose, then the key name-vs-ID contract, then a concrete example and the fallback. The example earns its space by showing argument composition; nothing is padded.

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 16-parameter read tool with full schema coverage, the description covers the non-obvious parts (name resolution, cross-tool routing) while the schema handles pagination, sort, rating bounds, and format. Return-shape explanation is only mildly missed since no output schema exists.

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 the meaningful semantic that name-based filters are resolved internally (name-as-identifier rather than ID), plus a worked example combining foods, exclude_foods, and keywords. That is more than a restatement of 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?

States a specific verb+resource ('High-level recipe search') and immediately distinguishes itself from list_recipes. An agent can pick between them without opening either schema.

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?

Says to use this when filtering by food/keyword/book names and to fall back to list_recipes for 'complex ID-based filtering'. The routing condition is explicit, though what counts as 'complex' is left to interpretation.

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