mcp-recipes

One dish, as each source writes it

compare_recipes

Read-onlyIdempotent

Compare recipe versions from multiple sources side by side, rescaling ingredients to the same servings and highlighting differences in quantities, measurements, yields, and published fields.

Instructions

Take a dish and show how each source writes it, side by side. Each source's closest match is read in full, and all of them can be rescaled to the same number of servings so the ingredient lists stand comparison. The answer states what differs and leaves it there: the quantities each asks for, what each measures in, what each yields, and which fields each source publishes at all. No version is ranked above another. Some sources carry reader ratings and some have no author and no rating by nature, so there is no score they share. When only one source answers, the answer says so and shows that one rather than presenting part of a comparison as the whole of it.

Input Schema

TableJSON Schema

Name	Required	Description
`dish`	Yes	The dish to compare, in any of the languages the sources publish in.
`sources`	No	Sources to compare, by id. Left out, every source is read, which is the point of this tool. Name two or three to put particular traditions side by side. The ids are the ones 'per_source' reports.
`sections`	No	Which parts of each version to return. Several full recipes is a lot of text.
`servings`	No	Rescale every version to this many, which is what makes the lists comparable.
`max_steps`	No	Steps to return per version.
`max_step_chars`	No	Characters kept per step. Raise it only if a step was cut mid-sentence.

Output Schema

TableJSON Schema

Name	Required	Description
`dish`	Yes
`notes`	Yes
`versions`	Yes
`per_source`	Yes
`differences`	Yes	What differs between the versions, stated as fact. No version is ranked.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv3.0.1Aug 29, 2026

addedInput schema / properties / sources

Added value: +{
+  "description": "Sources to compare, by id. Left out, every source is read, which is the point of this tool. Name two or three to put particular traditions side by side. The ids are the ones 'per_source' reports.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / versions / items / properties / rest_minutes

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Time the recipe stands, from a source that publishes it apart. It is in no other time here, and belongs to no other source's cooking time. Null where the source publishes none, which is not a dish that needs no rest."
+}

addedOutput schema / properties / versions / items / properties / steps_as_one_block

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Whether the source publishes the method as one block of prose rather than as steps of its own. Null where the source says neither, so a single entry is not read as step one of several."
+}

addedOutput schema / properties / versions / items / properties / withheld

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "parts": {
+          "description": "Which parts, named as 'ingredients' or 'method'.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "why": {
+          "description": "What the source says about keeping them back.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "parts",
+        "why"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "A part the source published nothing of because it keeps it for its subscribers. Null from a source that withholds nothing, which is a different statement from an empty list."
+}

changedOutput schema / properties / versions / items / required

Previous value: -[
-  "id",
-  "source",
-  "source_name",
-  "language",
-  "title",
-  "url",
-  "image_url",
-  "yield",
-  "ingredients",
-  "steps",
-  "prep_minutes",
-  "cook_minutes",
-  "total_minutes",
-  "category",
-  "author",
-  "rating",
-  "nutrition",
-  "equipment",
-  "tips",
-  "license",
-  "attribution",
-  "sections_returned",
-  "sections_omitted",
-  "scaling_summary"
-]New value: +[
+  "id",
+  "source",
+  "source_name",
+  "language",
+  "title",
+  "url",
+  "image_url",
+  "yield",
+  "ingredients",
+  "steps",
+  "prep_minutes",
+  "cook_minutes",
+  "total_minutes",
+  "rest_minutes",
+  "steps_as_one_block",
+  "withheld",
+  "category",
+  "author",
+  "rating",
+  "nutrition",
+  "equipment",
+  "tips",
+  "license",
+  "attribution",
+  "sections_returned",
+  "sections_omitted",
+  "scaling_summary"
+]

Changed4 schema fields changedv1.3.0Aug 11, 2026

addedOutput schema / properties / per_source / items / properties / preferred_by_name

Added value: +{
+  "description": "Whether this source's rows were arranged so the ones whose title names the dish come first. An order over one source's own rows, never a score against another source.",
+  "type": "boolean"
+}

addedOutput schema / properties / per_source / items / properties / read

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "error": {
+          "anyOf": [
+            {
+              "additionalProperties": false,
+              "properties": {
+                "code": {
+                  "type": "string"
+                },
+                "hint": {
+                  "type": "string"
+                },
+                "message": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "code",
+                "message"
+              ],
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "status": {
+          "enum": [
+            "read",
+            "failed"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "status",
+        "error"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "What became of the row this source offered, once it was opened. Null when no row was opened, which is what a search that did not answer and a search holding nothing both come to. A search and a read are two moments, and this is the second one."
+}

addedOutput schema / properties / per_source / items / properties / wordings

Added value: +{
+  "description": "Every wording this source was sent or held back from, in the order tried. A question written as a sentence is also sent in wordings derived from it, because these indexes answer the words they are handed. Counts here belong to one wording each and are never added.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "added": {
+        "anyOf": [
+          {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Rows it returned that no earlier wording had."
+      },
+      "count": {
+        "anyOf": [
+          {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Rows this wording returned. Null when it did not run."
+      },
+      "derivation": {
+        "description": "How this wording was derived from the question.",
+        "type": "string"
+      },
+      "error": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "code": {
+                "type": "string"
+              },
+              "hint": {
+                "type": "string"
+              },
+              "message": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "code",
+              "message"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "not_run_because": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Why it was held back. Null when it ran."
+      },
+      "query": {
+        "description": "What was sent to this source, or would have been.",
+        "type": "string"
+      },
+      "ran": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "query",
+      "derivation",
+      "ran",
+      "count",
+      "added",
+      "not_run_because",
+      "error"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / per_source / items / required

Previous value: -[
-  "source",
-  "name",
-  "status",
-  "count",
-  "reported_total",
-  "reported_total_means",
-  "skipped",
-  "cached",
-  "error"
-]New value: +[
+  "source",
+  "name",
+  "status",
+  "count",
+  "reported_total",
+  "reported_total_means",
+  "skipped",
+  "cached",
+  "preferred_by_name",
+  "wordings",
+  "error",
+  "read"
+]

First observedv1.0.0Aug 7, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnly, idempotent, and openWorld annotations, the description discloses meaningful behavioral traits: no ranking among versions, no shared score because some sources lack ratings, rescaled servings for comparability, and an explicit policy that a single matching source is shown rather than presenting a partial comparison. These details are not visible in the schema and materially shape output expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and each subsequent sentence earns its place by explaining comparison behavior, non-ranking, rating limitations, and single-source fallback. It is prose-style but compact and free of pointless decoration; every sentence contributes to correct invocation and interpretation.

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 and a full input schema, the description covers the essential behavioral context: what comparison means, how rescaling works, what is reported, what is not compared, and how edge cases are handled. An agent has enough information to select this tool and set expectations for the response without guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description reinforces the purpose of servings rescaling and the idea of matching sources, but it does not add significant parameter-level meaning beyond what the schema already documents. It earns the baseline without exceeding it.

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 and resource: 'Take a dish and show how each source writes it, side by side.' This unambiguously identifies the tool as a multi-source comparissor and distinguishes it from sibling tools like get_recipe or scale_ingredients by emphasizing side-by-side comparison and differing source treatments.

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 gives clear context for when this tool is appropriate: when an agent wants to see how different sources treat the same dish. It also explains the all-sources-by-default behavior and the single-source fallback. It does not explicitly name sibling alternatives or say 'use get_recipe instead for a single recipe,' but the comparative purpose is clear enough to infer the boundary.

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

Deploy Server