tooluniverse-clinical-guidelines

What it does

Search and retrieve evidence-based clinical practice guidelines from 12+ authoritative sources spanning 41 tools. Covers disease management guidelines, society recommendations, pharmacogenomics guidance, and patient resources.

KEY PRINCIPLES:

1. Multi-source search — Search ≥3 databases in parallel for comprehensive coverage
2. Source-appropriate queries — Match query style to each database's strengths
3. Condition + society specific — When user names a disease or society, use targeted tools
4. English queries first — Use English medical terms in all tool calls; respond in user's language
5. Cite sources — Every guideline result must include source organization and URL

Phase 0: Tool Verification (MANDATORY FIRST STEP)

Before searching, verify tools load:

from tooluniverse import ToolUniverse
tu = ToolUniverse()
tu.load_tools()
assert hasattr(tu.tools, 'NICE_Clinical_Guidelines_Search')

Correct call pattern (use either approach):

# Option A: direct attribute access
result = tu.tools.NICE_Clinical_Guidelines_Search(query='diabetes', limit=5)

# Option B: run_one_function
result = tu.run_one_function({'name': 'NICE_Clinical_Guidelines_Search', 'arguments': {'query': 'diabetes', 'limit': 5}})

Phase 1: Identify Query Strategy

Determine which tools to use based on the user's question: general disease guidelines, cardiology, oncology, diabetes, pharmacogenomics, living guidelines, etc., and prefer multi-source aggregation when possible.

Phase 2: Multi-Source Search

Follow the listed tools and formats to gather guideline results, with emphasis on general searches (NICE, GIN, TRIP) and specialty sources (ADA for diabetes, AHA/ACC for cardiology, NCCN for oncology, CPIC for pharmacogenomics).

Phase 3: Synthesize Results

Structure the output with a topic-oriented summary, followed by key recommendations per source, pharmacogenomics section if applicable, and a references section listing all URLs.

Phase 4: Decision Logic

Apply the decision logic for general disease guidelines, pharmacogenomics, and full-text retrieval, with fallback strategies if a source yields no results.

Critical Parameter Notes (Verified by Testing)

• Tool parameter conventions are precise: e.g., NICE_Clinical_Guidelines_Search requires query and limit; TRIP_Database_Guidelines_Search requires search_type='guidelines'.
• Optional parameters must be treated as optional (OpenAlex year_from/year_to).
• CPIC workflows require a sequence of calls; results are dict-wrapped.