eatmundo

Compare two dishes

compare_dishes

Read-onlyIdempotent

Compare two dishes ingredient by ingredient: shared items, what is unique to each, a match score, and - for the pairs that have one (nearly 900) - an editorial comparison paragraph in the requested language. Works for any two dishes in the corpus, whether or not they are an edge in the equivalence graph.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`a`	Yes	First dish: slug or name.
`b`	Yes	Second dish: slug or name.
`lang`	No	Language for titles, ingredient names and URLs.	en

Output Schema

TableJSON Schema

Name	Required	Description
`a`	Yes
`b`	Yes
`notes`	Yes
`score`	Yes
`only_a`	Yes
`only_b`	Yes
`paragraph`	Yes
`same_form`	Yes
`attribution`	Yes
`compare_url`	Yes
`score_basis`	Yes
`stored_score`	Yes
`is_graph_edge`	Yes
`below_threshold`	Yes
`excluded_generics`	Yes	Pantry staples deliberately excluded from BOTH the score and the ingredient lists above, because they match almost everything (flour/water/oil/salt/yeast for food, water/salt/sugar for drinks). They are present in the dishes - they are just not evidence of similarity.
`shared_ingredients`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 10, 2026

addedOutput schema / properties / excluded_generics

Added value: +{
+  "description": "Pantry staples deliberately excluded from BOTH the score and the ingredient lists above, because they match almost everything (flour/water/oil/salt/yeast for food, water/salt/sugar for drinks). They are present in the dishes - they are just not evidence of similarity.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "a",
-  "b",
-  "score",
-  "score_basis",
-  "is_graph_edge",
-  "stored_score",
-  "below_threshold",
-  "same_form",
-  "shared_ingredients",
-  "only_a",
-  "only_b",
-  "paragraph",
-  "compare_url",
-  "notes",
-  "attribution"
-]New value: +[
+  "a",
+  "b",
+  "score",
+  "score_basis",
+  "is_graph_edge",
+  "stored_score",
+  "below_threshold",
+  "same_form",
+  "shared_ingredients",
+  "only_a",
+  "only_b",
+  "excluded_generics",
+  "paragraph",
+  "compare_url",
+  "notes",
+  "attribution"
+]

First observedSep 10, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds real behavioral context the annotations cannot: the editorial paragraph exists for only ~900 pairs, so the agent knows output completeness varies by pair.

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?

One front-loaded sentence that leads with the core action and then layers the output detail and the availability caveat. No padding or repetition.

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?

An output schema exists, yet the description still summarizes the return shape and flags the partial-coverage caveat. Nothing needed to invoke or interpret this tool 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 baseline is 3, but the description adds meaning to lang by specifying it drives the editorial paragraph's language, going slightly beyond the schema's 'titles, ingredient names and URLs'.

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 (compare) and resource (two dishes) and enumerates what the comparison yields: shared items, unique items, match score, and an editorial paragraph. The clause about the equivalence graph implicitly separates it from find_similar_dishes.

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?

Explicitly states the tool works for ANY two dishes in the corpus, not just graph edges, which tells the agent when this is the right pick over find_similar_dishes. It stops short of naming that sibling or stating exclusions/alternatives outright.

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

All eatmundo 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?