Section guide

Tools, Skills, and Protocols

Tool contracts, skills, MCP, A2A, approval gates, and secure communication.

Use when agents need safe external capabilities or communication protocols.

Start with Skills
Finish with Human Approval Gates
Reader outcome

Leave able to expose capabilities through typed, authorized, reviewable contracts.

Reusable artifact

A capability contract with permissions, approval points, protocol envelope, and audit record.

Reading order

6 chapters
  1. 01
    Skills Pattern · Intermediate 12-25 min pattern review Builder · Security

    Skills package procedural knowledge as discoverable, versioned folders of instructions, references, scripts, templates, assets, and tests.

  2. 02
    Tool Capability Design Guide · Intermediate 10-20 min read Builder · Security

    Tool Capability Design shows how to expose external actions through narrow schemas, permissions, examples, traces, and safe errors.

  3. 03
    MCP-first Tool Use Pattern · Intermediate 12-25 min pattern review Builder · Security

    MCP-first tool use separates tool capability from agent logic through manifests, validation, invocation, and structured results.

  4. 04
    A2A Agent Interoperability Pattern · Intermediate 12-25 min pattern review Builder · Security

    A2A makes agents discoverable and callable across process, team, runtime, and vendor boundaries.

  5. 05
    Secure Agent Communication Pattern · Intermediate 12-25 min pattern review Builder · Security

    Secure communication protects messages between agents with authentication, integrity, confidentiality, and policy checks.

  6. 06
    Human Approval Gates Pattern · Intermediate 12-25 min pattern review Builder · Security

    Human approval gates pause execution before sensitive, expensive, destructive, or externally visible actions.