Loading ToolBench
Fetches comprehensive, reliable medical information about diseases from StatPearls, a trusted source of peer-reviewed medical content.
Single tool with adequate naming and schema, but description lacks specificity for LLM selection. Tool name 'statpearls_disease_info' follows verb_noun convention and is clear. Input schema is present with proper types and descriptions for both parameters. However, the tool description (194 chars) is generic and does not explain WHEN to use this tool vs alternatives, what prerequisites exist, or how results are structured. Parameter descriptions are present but lack format constraints (e.g., no guidance on query length, expected disease name formats). Output schema is not documented, LLMs cannot predict the structure of returned content. Error handling exists but is minimal (generic error messages without recovery guidance).
Fetches comprehensive, reliable medical information about diseases from StatPearls, a trusted source of peer-reviewed medical content. Use this tool to get detailed information about diseases, conditions, symptoms, treatments, and medical concepts. Returns structured information including etiology, epidemiology, pathophysiology, clinical features, diagnosis, treatment, and prognosis when available.
Output schema not documented. Tool returns unstructured text; LLMs cannot plan downstream operations or extract structured fields. Baseline: 100% of A+ tools document return types.
Tool description lacks selection guidance. Does not explain WHEN to call this vs a general web search, what prerequisites exist (e.g., internet access), or what data structures are returned. Baseline: descriptions should answer what, when, and what it returns.
Parameter 'query' lacks format constraints. No guidance on minimum/maximum length, expected input format (disease name vs symptom vs ICD code), or examples of valid queries. LLMs may pass invalid inputs.
Error handling is generic. Errors return raw exception messages without recovery guidance. Pattern: errors should tell LLM what to do next (e.g., 'Query too broad, try a specific disease name').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
maxLength parameter default (50000 chars) is not justified. No guidance on typical response sizes, truncation behavior, or whether partial results are acceptable. LLMs may not understand trade-offs.