Loading ToolBench
FastMCP server for D&D rules lookup, character sheet translation, and build validation. Provides tools for searching game rules, retrieving entries, translating terms, and managing D&D character attributes.
Server has 6 well-structured tools with complete input schemas and descriptions. Tool names follow verb_noun convention (suche, hol, uebersetze, liste, pruefe). All parameters have type definitions and descriptions. However, output schemas are not documented in the provided source, and error handling guidance is minimal. Descriptions are solid (100-200 chars) but lack dependency hints and recovery guidance. No evidence of parameter validation or constraint enforcement beyond enums.
Retrieves calculated attribute values for a D&D character (ability modifiers, skill bonuses, AC, initiative, etc.). Computes derived values from base attributes and proficiencies.
Retrieves the full details of a specific rules entry by ID and category. Returns complete text, metadata, and source information. Use after search to get full entry details.
Lists available options for character sheet attributes (ability scores, skills, languages, proficiencies, etc.). Returns valid choices for dropdown/selection fields in character building.
Validates a D&D character build for rule compliance. Checks ability score arrays, class/race combinations, feat prerequisites, spell selections, and equipment legality. Returns validation errors and warnings.
Searches the D&D rules database by category and query term. Returns matching entries with relevance ranking. Searches across all available sources (rulebooks, errata, adventures). Returns empty results with explicit hint if nothing matches - never answer from general knowledge.
Translates D&D game terms between German and English. Returns the official translation from the glossary with context and usage notes. Handles abbreviations and variant spellings.
Output schemas not documented. LLMs cannot plan downstream calls or extract required fields without knowing response structure.
Error handling lacks recovery guidance. No indication of retryable vs fatal errors, or what the LLM should do next on failure.
foliant_liste_optionen parameter 'attribut' lacks enum constraint. Free-form string invites hallucinated values instead of valid attribute categories.
foliant_pruefe_build 'charakter' parameter is an untyped object. No schema for required/optional fields, structure, or nested types.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
No pagination support documented for foliant_suche_bestand despite 'limit' parameter. No indication of total count, next_cursor, or handling of large result sets.