Tools and MCP
Typed tools connect an agent to actions and data. The Model Context Protocol standardizes how compatible clients discover and invoke those capabilities.
Use it when
- An agent needs current data or actions beyond its built-in environment.
- Several clients should reuse the same server and capability definitions.
- Authentication, consent, schemas, and error behavior need an explicit boundary.
Choose another layer when
- Static knowledge that belongs in a reference file or retrieval index.
- A vague mega-tool whose inputs, side effects, or failure modes cannot be described.
Production path
Build it in this order
- 01
Design the tool contract first
Name one capability, define typed inputs and outputs, describe side effects, and return errors the agent can act on.
Quality check: A model can choose the tool and construct valid arguments from its description alone.
- 02
Separate reads from writes
Expose least-privilege capabilities, make destructive or external actions obvious, and require appropriate consent.
Quality check: A read-only workflow cannot accidentally perform a mutation.
- 03
Test discovery and recovery
Validate schemas against real clients, exercise authentication and failures, and log calls without exposing secrets.
Quality check: The same representative task succeeds—or fails clearly—across supported clients.
Artifacts you may see
- mcp.json
- .mcp.json
- server manifests
- tool schemas
Connected layers
Evidence ledger
Primary documentation behind this guide
Provider-specific behavior is sourced to that provider. Open standards are sourced to their specifications and official maintainers.