mcptokensaver

The format preserves all fields — name, description, and input schema are all there, just encoded with pipes instead of braces and quotes. It's lossless, not a truncation. I should have made that…

Fair point. I used tiktoken (cl100k_base) for all measurements. The 2,034 token count is from the actual JSON tool listing returned by 5 MCP servers (filesystem, memory, sequential-thinking, sqlite, t…

Good point - Claude Code does defer tool loading when definitions exceed 10% of context. That helps a lot. But they are solving different problems. Deferred loading is "don't load tools unti…