# Common Mistakes to Avoid

1. **Using detail='full' with limit=50**
   - Result: ~40k tokens consumed
   - Fix: Start with detail='minimal', escalate selectively

2. **Not using intent parameter**
   - Result: Mixed ranking, less relevant results
   - Fix: Choose intent based on query type

3. **Over-filtering stores too early**
   - Result: Miss better answers in other libraries
   - Fix: Search broadly first, then narrow

4. **Setting limit too low (1-2)**
   - Result: Miss relevant alternatives
   - Fix: Use limit=5 minimum, more for discovery

5. **Not checking relevance scores**
   - Result: Waste time on low-relevance results
   - Fix: Filter by score > 0.7 before deep dive