Tool Schema
A tool schema defines the fields and types an AI agent must use when calling an external tool.
Category
Agent Reliability
These terms cover structured tools, controlled retries, escalation to people, and traceable actions.
How to recognize this theme
Terms used to make AI agents safer and easier to operate.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Retry Policy
A retry policy controls when and how an agent repeats a failed request without looping indefinitely.
Human Handoff
A human handoff transfers an uncertain or sensitive task from an AI agent to a person.
Audit Trail
An audit trail records an agent's inputs, decisions, tool calls, and outputs for later review.