We define and construct the ‘semantic complexity index’ (SCI) which captures the marginal contribution of multi-clausal phrases (e.g., ‘slowdown in business activity’); and adjectives, adverbs and adversative conjunctions (e.g., ‘greater’, ‘slightly’, ‘however’) which alter the connotation of financial texts. More semantic complexity makes text difficult to interpret, which leads to poor readability, increased ambiguity and more investor uncertainty. We show that during 1994-2018, yearly SCIs of US firms' MD&A section display significantly positive association with firms' subsequent volatility and standardized unexpected earnings. We find that firms downplay negative information and exaggerate positive information, but markets react to such firms by associating higher subsequent volatility to them. We also show that the SEC Plain English Rule (October 1998) has reduced the semantic complexity of US firms' 10-Ks, and hence has improved readability observations at odds with other popular readability metrics.