Nutrition data for AI agents, powered by Edamam’s database of ~900,000 foods and 680,000+ UPC codes.
Scored across 2 tools
The two tools split cleanly along input modality: image vs. plain text. Each description explicitly tells the caller when to use the other tool, eliminating any selection ambiguity.
Both names follow the same snake_case verb_noun pattern (analyze_food_image, get_food_nutrition) with clear resource-oriented nouns. No convention mixing.
Two tools is thin for a nutrition API surface; a server this focused is plausible, but it sits at the borderline where a single additional capability would materially broaden usefulness.
Nutrition analysis from image and text is covered, but there is no food database search, autocomplete, or recipe/meal-level nutrition lookup, so callers needing to resolve or browse foods have no path other than free-text queries.
Identify food in a photograph and return a full nutritional breakdown.
Uses Edamam's AI Vision API (beta) to detect each dish on the plate, estimate its ingredients, and calculate nutrition. Every dish is analyzed independently, so multi-dish plates return one entry per dish. Works best with clear, well-lit photos.
The image is supplied as base64-encoded bytes (the API accepts only a raw image upload, not a URL), most conveniently as a data URI: "data:image/jpeg;base64,...". A caller with a remote URL must download the image itself and base64-encode the bytes.
To look up nutrition from a text description instead, use get_food_nutrition.
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | A base64 data URI (e.g. "data:image/jpeg;base64,...") — or a bare base64 string — of a food photograph. |
| Name | Required | Description |
|---|---|---|
| dishes | Yes | One nutrition summary per detected dish; a single-dish photo yields a one-element list, a multi-dish plate yields several. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the load and does so well: it names the backing service and its beta status, explains per-dish independent analysis so multi-dish plates return multiple entries, and states the API accepts only raw image upload, not URLs. It omits operational behavior such as latency, failure modes, or rate limits, which keeps it from a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose, then behavior, then input mechanics, then the sibling routing — a sensible order. The data URI example is repeated in both the description and the schema, a minor redundancy that costs it a point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter tool with an output schema, the description covers everything an agent needs: what it does, what input form is required, how multi-dish results are structured, and when to pick the alternative. Return-value details are correctly left to the output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 real meaning the schema does not: a remote URL must be downloaded and re-encoded by the caller, and the bare-base64 alternative is spelled out. It stops short of naming accepted image formats or size limits.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Identify food in a photograph and return a full nutritional breakdown") and immediately names the sibling it is not (get_food_nutrition). An agent can distinguish image-based analysis from text lookup 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit routing rule: use get_food_nutrition when starting from a text description, and this tool when starting from a photo. It also adds an applicability condition ("Works best with clear, well-lit photos") that tells the agent when results may degrade.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up nutrition facts for one or more foods described in plain text.
Use this tool for any question about calories, macros, or nutrients for a named food or meal. Each query is a natural-language phrase describing one food item; the API identifies the food, resolves the quantity and unit, and returns a full nutrient breakdown. If the user provides a food photograph rather than a text description, use analyze_food_image instead.
Returns a list of dicts, one per query. Each dict has: food (name,
food_id, amount, unit, weight_g, ingredients), macronutrients (calories,
protein, carbs, fat, etc.), micronutrients (vitamins and minerals),
diet_flags, health_flags, and status.
Returns {"error": ..., "query": ...} for any item that cannot be identified.
| Name | Required | Description | Default |
|---|---|---|---|
| queries | Yes | One natural-language phrase per food item. Supported formats: plain name ("cheddar cheese", defaults to 100 g), quantity + unit ("1 cup rice", "200g chicken breast"), or UPC/EAN barcode ("049000042566", 8-14 digits). Keep compound food names as a single entry — "carrot cake", "chicken noodle soup", and "grilled cheese sandwich" are each one food, not multiple. Only split into separate entries when the user is clearly listing multiple distinct foods — e.g. "1 croissant and 1 egg" → ["1 croissant", "1 egg"]. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it explains natural-language identification, quantity/unit resolution, one result per query, and per-item error returns. It leaves out ambiguity handling, rate limits, or permission context, so it is strong but not fully exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with purpose and usage, then structured around behavior and returns. It is clear and mostly efficient, though the detailed return-field enumeration is somewhat redundant because an output schema exists.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter lookup tool with full schema coverage and an output schema, the definition includes the key context: what it returns per query, error behavior, and the photo alternative. Nothing essential for correct invocation appears to be missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the schema already documents plain names, quantity+unit formats, barcodes, defaults, and splitting compound foods. The description adds only a light restatement that each query describes one food item and that the API resolves quantity/unit, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: "Look up nutrition facts for one or more foods described in plain text." It also explicitly distinguishes this text-based lookup from analyze_food_image for photographs, so the agent can select between siblings without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives clear trigger conditions: use for questions about calories, macros, or nutrients for a named food or meal. It also names the photo alternative and when to use it, covering both when to use this tool and when to switch to the sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_food_imageget_food_nutrition
Add one secure layer between your agents and this server.