Skip to main content
Glama

Search recipes

search_recipes
Read-onlyIdempotent

Use this when the user wants ideas or recipes to cook, by dish, ingredient, cuisine, diet, time or rating, or just wants to browse. query is optional: leave it out to browse by tags and sort. Searches the public Only Recipes library and returns a grid of recipes. Not for the user's own recipes (use list_my_recipes) or for a pasted link (use import_recipe). Plain keywords need no filters; call get_filters first only to filter by tag. Without a linked account, query matches whole words and word prefixes in the recipe name, a short description summary and tag slugs (not arbitrary substrings), results can lag new recipes and votes by up to a day, and sourceUrl is always null.

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 (1-indexed, default 1)
sortNoSort order: recent (newest), popular (most votes), rating (highest rated), trending (recently imported)
tagsNoTag slugs to filter by (e.g. ['italian', 'dinner', 'vegetarian'])
queryNoText search query to match recipe name or description
pageSizeNoResults per page (default 12, max 50)

Output Schema

NameRequiredDescriptionDefault
pageNo
statusNo
messageNo
recipesYes
pageSizeNo
pageCountNo
totalCountYes
unknownTagsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds substantial context: query is optional for browsing, anonymous search matches whole words and prefixes rather than substrings, results can lag new recipes and votes by up to a day, and sourceUrl is always null without a linked account. These are non-obvious operational traits not available from structured fields, though permission/account-linking mechanics could be stated slightly more directly.

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 primary intent and exclusions before the edge-case semantics. Dense but every clause carries information; the final sentence is long and packs account-specific caveats that could be broken out, but nothing is expendable.

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?

With an output schema present, the description needn't explain return values and doesn't. It covers the remaining agent-critical unknowns: anonymous vs linked-account behavior, result freshness, tag-filter prerequisite, and sibling routing. Nothing needed to call it correctly is missing.

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 the schema documents page, sort, tags, query and pageSize; the baseline is 3. The description goes beyond it by clarifying that query is optional, that omitting it browses by tags and sort, and by defining what query actually matches (name, description summary, tag slugs) in the anonymous case, which the schema's short 'match recipe name or description' understates.

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 plus the scoping facets (dish, ingredient, cuisine, diet, time, rating, browse) and what is returned ('a grid of recipes'). It explicitly distinguishes itself from list_my_recipes and import_recipe, so an agent can pick it without opening a 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?

Gives explicit when-to-use, when-not-to-use with named alternatives ('Not for the user's own recipes (use list_my_recipes) or for a pasted link (use import_recipe)'), and a sequencing rule: call get_filters first only when filtering by tag, plain keywords need no filters.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources