Tool
A tool is any external capability an AI agent can call — querying a system, fetching a document, executing an action — exposed through a declared interface with typed inputs and outputs. In a governed platform, each tool call passes a policy check (allow, ask or deny) before it executes.
In NeoXam Agents
All tools are MCP servers with declared schemas, and every agent declares a per-tool allow/ask/deny policy in its descriptor: 'allow' executes, 'ask' pauses for human approval, 'deny' blocks. Irreversible side effects default to ask or deny, and an 'allow' on a sensitive tool requires a written rationale enforced by CI.
Related terms
See it at work
Reconciliation break investigation
Shipped — V0 pilotOne click on a break: the agent investigates match history and pricing, then returns root cause, evidence and a recommended action — fully traced.
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform