A team is building an MCP server that integrates with Salesforce. Their tool catalog includes: search_contacts, get_contact_by_id, update_contact, create_opportunity, get_opportunity_pipeline, update_opportunity_stage, generate_report, and send_email. This is 8 tools. During testing, Claude occasionally picks the wrong tool (e.g., search_contacts when get_contact_by_id is more appropriate). What improves tool selection accuracy?