Schemas and Descriptors
Machine-readable structures for protocol explanation and validation.
Use this page when you need the strict machine-readable contract layer that tooling and validation can rely on.
Before you continue
Read these first if you want the current page to make more sense in the wider handbook.
Why schemas matter
Agents need more than prose. They need stable shapes for validation, routing, and tooling.
What to expose
- Identity format and field constraints.
- Core message envelope structure.
- Known message types and required fields.
- Endpoint contracts and expected response shapes.
Recommended practice
Put the human-readable reasoning in the descriptor layer and reserve schema payloads for strictly machine-readable contracts.
Related pages
Open these pages when you want adjacent concepts, neighboring entities, or connected implementation context.
Examples
Examples make the MCP section usable, they turn abstract descriptions into a sequence an agent or implementer can actually follow.
Discovery
This page explains the first machine-facing handshake, what an agent needs to learn before deeper integration and why discovery should stay boring.
Next reading
Use this path if you want a cleaner progression through the handbook after this page.