OpenAPI is primarily for machine-to-machine which needs determinism and optimized for some cases (e.g. time in unix format with ms accuracy). MCP is optimized for another use case where LLM has many limitations but has good "understanding" of text. instead of sending `{ user: {id: 123123123123, first_name: "XYZYZYZ", "last_name": "SDFSDF", "gender": "..."..... } }` you could return "Mr XYZYZYZ" or "Mrs XYZYZYZ"

llm doesn't need all these and can't parse it anyway without additional tools (e.g. why should it spend tokens even trying to convert unix timestamp to understand the time)

I thought the whole point of structuring the data was to avoid the LLM from hallucinating/forcing it to conform to a spec?