Skip to main content
Glama
smeet666

mcp-recipes

Search every recipe source at once

search_recipes
Read-onlyIdempotent

Search every recipe source at once for a dish or ingredient, get one merged list where each entry carries the ID of its source for later retrieval.

Instructions

Search every recipe source this server reads, at the same time, for a dish or an ingredient, and get one merged list. Each row carries the id get_recipe takes, and that id names the source it came from, so nothing has to be guessed afterwards. The sources are written in different languages and count their own results differently, so 'per_source' says what each one answered, what its own number means, and names any that failed. A short list is never evidence of what exists. Some sources keep recipes and reference pages together, so a row can be a page about an ingredient rather than a recipe using it. Only get_recipe can tell them apart, and it says when a page carries no ingredient list. The query goes to each source's own search as free text. There is no filtering: a word naming a diet, a time or a calorie count matches only where that source's index happens to carry it. Rows are interleaved one source at a time rather than ranked, because the sources share no score that could order them against each other.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesA dish or an ingredient, in any of the languages the sources publish in.
sourcesNoSources to ask, by id. Left out, they are all asked, which is the point of this tool. The ids are the ones 'per_source' reports.
limit_per_sourceNoRows to take from each source, so one source cannot fill the whole list.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesYes
orderYesHow the list was built, in words.
queryYes
resultsYes
per_sourceYes
result_countYesRows in this answer, across every source.
Behavior5/5

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

Annotations already declare the tool as read-only, open-world, idempotent, and non-destructive, and the description adds substantial behavioral context beyond that: merged and interleaved results, per-source reporting with failure names, language differences, absence of cross-source ranking, potential non-recipe rows, and the fallback to get_recipe for disambiguation. These are crucial runtime behaviors not evident from the schema or annotations.

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?

The description is long but every sentence carries meaningful caveats or operational details. It is front-loaded with the core purpose and then systematically addresses result structure, per_source, limitations, and disambiguation. It could be tightened slightly, but it remains focused and non-redundant for a tool with this many behavioral subtleties.

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?

Given the tool's complexity and the presence of an output schema, the description covers all essential context: what the merged list looks like, how per_source reports per-source results and failures, why no ranking is applied, the possibility of ingredient pages instead of recipes, and how get_recipe resolves ambiguity. No critical operational detail seems 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?

The schema already documents all three parameters (100% coverage), so the baseline is 3. The description enriches this by explaining that 'query' is free text sent to each source's own search, that omitting 'sources' asks all sources (which is 'the point of this tool'), that source ids match those in 'per_source', and that 'limit_per_source' prevents one source from dominating the list. This adds real meaning beyond 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?

The description opens with a specific verb+resource: 'Search every recipe source this server reads, at the same time, for a dish or an ingredient, and get one merged list.' It clearly distinguishes from sibling tools like get_recipe by emphasizing multi-source search and the id/name mapping that get_recipe will later consume.

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?

The description clearly conveys when to use this tool: when you want to search all recipe sources at once, and it contrasts with get_recipe by noting that only get_recipe can differentiate recipes from pages. It also explains that filtered queries are not supported ('There is no filtering'), implying this tool is for broad free-text search. However, it doesn't explicitly say 'use get_recipe when you already have an id' or provide a when-not-to-use list for all siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smeet666/mcp-recipes'

If you have feedback or need assistance with the MCP directory API, please join our Discord server