Loading ToolBench
MCP Server for nutrition data — USDA FoodData Central with 1M+ foods, nutrients, vitamins and dietary analysis
Server has 8 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (positive), but many are in German and lack LLM-optimized structure. Parameter descriptions exist but are sparse. No output schemas documented. Error handling is minimal. Tool naming follows verb_noun convention (good), but descriptions lack actionable context for LLM selection. No tool annotations (readOnlyHint, etc.). Average tool quality ~52/100.
Berechnet wie viel Prozent des Tagesbedarfs ein Lebensmittel deckt.
Zwei Lebensmittel naehrwerttechnisch vergleichen.
Lebensmittel mit hohem Gehalt eines bestimmten Naehrstoffs finden.
Taeglich empfohlene Naehrstoffzufuhr (DRI) fuer Erwachsene anzeigen. Zeigt die offiziellen FDA Daily Values fuer alle wichtigen Naehrstoffe.
Verfuegbare Lebensmittelkategorien und Datentypen in USDA FoodData Central anzeigen.
Get detailed information about a specific nutrient.
No output schemas documented. LLMs cannot predict response structure or plan downstream tool calls. Tools return dicts but no formal schema specification visible.
Descriptions are in German and lack LLM-optimized structure. Missing WHEN to use, prerequisites, and actionable context. E.g., 'Lebensmittel in der USDA FoodData Central Datenbank suchen' lacks guidance on when to call vs. tool_find_foods_high_in.
No error handling or recovery guidance. Tools return raw API responses without actionable error messages. E.g., if search_foods fails, no guidance on retry strategy or alternatives.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 48 | 2026-07-28+ | v2 |
Vollstaendige Naehrwertdaten fuer ein Lebensmittel abrufen.
Lebensmittel in der USDA FoodData Central Datenbank suchen (1M+ Eintraege).
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are read-only but this is not declared in schema, forcing LLMs to infer safety.
Parameter descriptions are minimal. E.g., 'nutrient' in tool_find_foods_high_in lacks format guidance (case-sensitive? aliases?). 'limit' in tool_search_food states 'max. 25' but no minimum or validation logic visible.