Every brief in this series uses the terms “agent” and “tool” as if everyone knew what that means. This brief explains those terms.
A chatbot is a simple conversation. You ask, it answers from what it already knows. An agent has a job list: It can stop mid-answer, go get something it does not know, and come back — then decide if it needs to go get something else before it is done.
Every one of those trips is a tool call. An AI model can write and reason, but it cannot check today's date, look up a record, or send an email by itself. The model needs tools to do those tasks. A tool extends the AI with one specific, narrow action it can trigger.
A tool can be almost anything a business already uses. If a person could look something up or take a specific action, an agent leverage a tool that does the same thing — including searching the open web.
Steps 2 and 3 repeat as many times as the job needs — the agent decides, one trip at a time.
“What is my copay for tomorrow's visit?” The agent makes two tool calls to find out.
Without a shared standard, every agent would need custom wiring for every tool it might use — a separate connector per pair, rebuilt each time either the agent or tool changes.
MCP — Model Context Protocol — fixes that. It is a shared job description any tool can implement. Once a tool understands this protocol, any agent that also speaks it can find that tool, see what it does, and use it. Think of it like a wall socket instead of a bare wire: once a machine has the right plug, it works in any socket built to the same standard.
MCP is not one company's product — it is an open specification. Database providers, SaaS applications, and common data sources are now providing their services and data as an MCP tool, so any agent can query or interact without a custom connector.
Every tool an agent can call is also a door. Standards that makes doors easy to add will also make it easy to add too many. An unreviewed tool is the same risk as an unapproved app, but it's faster, and running all day.
Full paper, 10 pages — iterate.ai/partners/netapp/private-ai-education-and-certification-program. On deciding which model handles a job, see What Is a Harness?; on seeing every call after the fact, You Cannot Govern What You Cannot See.
A joint educational series on private AI and the AIPod Mini. NetApp® — the governed data-control layer. Iterate.ai — the private intelligence layer.
