Prior research on memory mechanisms in RAG-based conversational systems has primarily focused on storage and retrieval methods. This study investigates how memories with distinct functional roles influence response quality across varying contexts. The authors present a fine-grained taxonomy of conversational memory to classify retrieved items into specific role types. They also design a user-centric evaluation framework that simulates user perspectives to address limitations in reference-based assessments. Comparative experiments were conducted on long-term datasets using frontier large language models to analyze these effects. Results indicate that clarifying memory enhances factual accuracy and constraint awareness, leading to more correct and personalized responses. Conversely, irrelevant memory was found to reduce topic relevance and degrade constraint awareness capabilities. These findings demonstrate how different memory types can be leveraged to improve personalization in conversational agents.