# Tools, skills & protocols

The action and knowledge interfaces through which agents use tools, load procedural skills, access enterprise context, and collaborate with other agents.

core-concept · Multi-agent & protocols · maturing · Reviewed 2026-08-09

## Definition

The action and knowledge interfaces through which agents use tools, load procedural skills, access enterprise context, and collaborate with other agents. Interoperability expands what agents can do; it does not decide what they should be trusted to do.

Protocol milestones exist, while security and governance profiles continue to evolve.

## Why it matters

Interoperability expands what agents can do; it does not decide what they should be trusted to do.

The operating shift is from “One assistant with plugins” to “Composable capability fabric.”

## System anatomy

- **Practice 1:** Keep tool contracts narrow and typed
- **Practice 2:** Separate protocol compatibility from authorization
- **Practice 3:** Record tool source, version, identity, and effect



## Important distinctions

- **One assistant with plugins:** This concept moves the engineering system toward composable capability fabric.



## Implementation signals

- Keep tool contracts narrow and typed
- Separate protocol compatibility from authorization
- Record tool source, version, identity, and effect

## Failure modes

- Tool descriptions granting accidental authority
- Protocol support being mistaken for trust



## Related knowledge

- [Agent identity & delegated authority](https://aisdlc.ai/agentic-engineering/agent-identity) — The identity and authorization discipline that treats an enterprise agent as a non-human principal with attributable, purpose-bound, time-bound permissions.
- [Agent execution substrate](https://aisdlc.ai/agentic-engineering/execution-substrate) — The isolated, stateful environment in which agents observe and act, including compute, filesystem, browser, network, credentials, resource limits, and session lifecycle.
- [Context engineering](https://aisdlc.ai/agentic-engineering/context-engineering) — The deliberate selection and maintenance of instructions, knowledge, tools, state, examples, and artifacts within a finite model attention budget.

## Sources and further study

- [Model Context Protocol — Enterprise-Managed Authorization for MCP](https://blog.modelcontextprotocol.io/posts/enterprise-managed-auth/) — An emerging authorization pattern for enterprise-managed agent access to MCP servers. **Use:** Standard or protocol. **Limitation:** A specification defines an interface or control pattern; conformance alone does not establish authorization, security, or fitness for a use case.
- [A2A Project — Agent2Agent Protocol v1.0](https://a2a-protocol.org/latest/announcing-1.0/) — A protocol milestone for interoperable communication and collaboration between agents. **Use:** Standard or protocol. **Limitation:** A specification defines an interface or control pattern; conformance alone does not establish authorization, security, or fitness for a use case.
- [NIST — AI Agent Standards Initiative](https://www.nist.gov/artificial-intelligence/ai-agent-standards-initiative) — A standards initiative addressing secure, interoperable adoption of AI agents. **Use:** Official guidance. **Limitation:** Guidance describes recommended practice; citation does not prove that a control is implemented or effective in a particular environment.

---

This library synthesizes cited research, standards, official documentation, and clearly attributed practitioner perspectives. Maturity describes the state of a concept—not vendor endorsement, production readiness, or permission to deploy. Benchmarks and demonstrations do not replace use-case evaluation, governed controls, independent verification, or named human release authority.