Readability (Flesch)
How to fix it
Use plainer words and shorter sentences. Aim for ~50–70 for general audiences.
Evidence
Good practice. Widely recommended, but no platform has confirmed it matters for AI answers.
No published source; see the tier above for what that means.
How it counts
- Weight: 1 (info) × 0.5 (evidence tier), within the Answer-extraction readiness module, which carries 30% of the overall score.
- Pass counts fully, warn counts half, fail counts nothing.