Loading ToolBench
Three tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Tool names follow verb_noun convention (get_*), which is good. However, descriptions are minimal (10-50 chars), parameter descriptions lack detail on constraints and formats, and output schemas are not formally documented. Error handling exists but lacks recovery guidance. No tool annotations (readOnlyHint, etc.). The resource implementation is present but not counted toward tool scoring.
현재 날짜와 시간 정보를 다양한 형식으로 반환합니다.
주식에 대한 기본 정보를 조회합니다.
YFinance를 사용하여 특정 기간의 주식 가격 정보를 조회합니다.
Descriptions are too short (10-50 chars) to guide LLM tool selection. Current descriptions lack WHEN to use, WHAT it returns, and prerequisites.
Output schemas are not documented. LLMs cannot plan downstream calls or extract fields without knowing the response structure. get_stock_price_history returns List[Dict] but field names and types are not declared.
Parameter descriptions lack format constraints and validation rules. 'start' and 'end' say 'YYYY-MM-DD format' but do not specify range, whether past dates are allowed, or what happens if end < start. 'timezone' accepts any string but should enumerate common zones or document validation.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | 2026-07-28+ | v2 |
Error messages are generic ('주식 데이터 조회 중 오류가 발생했습니다'). Current errors provide no recovery guidance.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All three tools are read-only and idempotent, but this is not declared in the schema. LLMs cannot infer safety properties without explicit hints.