Children increasingly rely on web search engines to support their learning and exploration. However, conventional search systems are not optimised for their developmental stage, often returning information that is linguistically complex or educationally irrelevant. The retrieved results are often written at a higher reading grade level than children can easily comprehend, resulting in poor engagement and learning outcomes. This research investigates whether substituting simpler vocabulary into search queries can improve the educational relevance and readability of retrieved web content. We develop a reformulation pipeline consisting of: (1) a rule-based method that substitutes key query terms with synonyms ranked by Age of Acquisition (AoA) scores, and (2) a computational intelligence approach that uses a Large Language Model (LLM) to generate child-friendly rephrasings. The results retrieved from the queries are evaluated across two dimensions: readability and educational relevance. Our results show that rule-based reformulations improve readability, but retrieved results stayed consistent in terms of educational relevance. LLM-based reformulations enhance educational relevance; however, they don’t improve readability. This trade-off highlights the complementary strengths of both methods and underlines the potential of direct query reformulation to make web search more accessible and educationally effective for children.