A new specification called TERSE Tool Catalog (TTC) has been introduced to significantly reduce the token usage for AI agent tool catalogs. Current Model Context Protocol (MCP) JSON Schema definitions are verbose and consume excessive tokens, impacting cost and performance. TTC offers a more semantic and condensed format, including explicit fields for purpose, trigger conditions, error handling, and tags, resulting in an average 66.6% token reduction while enhancing tool selection accuracy. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Reduces token costs and improves tool selection accuracy for AI agents, potentially lowering operational expenses and enhancing performance.
RANK_REASON This is a new specification for optimizing AI agent tool catalogs, not a direct release from a frontier model lab or a significant industry-wide event.