Skip to main content
Glama

FitzTopPicks APIs: calendars, recipes, names, places, sizes and more

Parse recipe ingredient lines

parse_ingredients
Read-onlyIdempotent

Parse recipe ingredient lines (English or Spanish) into amount, unit, item, prep, notes, optional flag, canonical key, grocery aisle, confidence and any unparsed remainder, with keyword flags for the major US food allergens (text matching, not a safety check). Send one "line" (e.g. "2 (14.5 oz) cans diced tomatoes, drained") or up to 100 "lines". More APIs from FitzTopPicks: https://fitztoppicks.com/apis?utm_source=mcp-api&utm_medium=mcp&utm_campaign=more-apis

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": "parse_ingredients"
  }
}

Input Schema

NameRequiredDescriptionDefault
lineNoOne ingredient line.
linesNoUp to 100 ingredient lines (send this or "line").

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavior: language support, the 100-line batch cap, that unparsed remainder is returned rather than dropped, and the important caveat that allergen flags are text matching and not a safety check. It stops short of describing failure behavior or ordering of batch results.

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 parse scope and output fields, and the input-shape guidance follows immediately. The first sentence is a dense ~45-word enumeration and the trailing promotional URL for other APIs does not earn its place, but no informational content is wasted.

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 no output schema, the description carries the full burden and does so by naming every returned field (amount, unit, item, prep, notes, optional flag, canonical key, aisle, confidence, remainder). Input limits, batch size, supported languages, and the allergen-flag caveat are all covered for a two-parameter read-only tool.

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 description coverage is 100%, so both parameters are already documented and the baseline is 3. The description adds a worked example ("2 (14.5 oz) cans diced tomatoes, drained") that demonstrates nested quantity/unit handling, and restates the one-or-many constraint, giving modest 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?

States a specific verb and resource ("Parse recipe ingredient lines") plus scope (English or Spanish) and enumerates the exact output fields produced, so an agent knows precisely what it gets back. Parsing is clearly distinguishable from sibling operations like convert_ingredient or scale_recipe by the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives input-shape guidance (send one "line" or up to 100 "lines") and a concrete example line, which is genuinely useful. However, it never says when to use this versus convert_ingredient or scale_recipe, nor any prerequisites or exclusions, so routing between siblings is left to inference.

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