Agent-Native Tools
Source-grounded pack with Agent Tool Fit Check, Tool Context Contract, and Agent UX Review, plus 1 more.
Use this pack when
Choose this pack when the work touches Agent-Native Tools and you need a bounded workflow with explicit inputs, a defined output, and human review gates.
Included workflows
Choose the job in front of you.
4 source-grounded skills. Load one workflow at a time.
Agent Tool Fit Check
Use this workflow when deciding whether a software product exposes a real delegated-work surface for agents or merely wraps a human UI and low-level API calls.
Output Return an agenttoolfitreport containing:
Tool Context Contract
Use this workflow when specifying an agent-facing work contract that makes business objects, actions, state, context projections, errors, and side effects explicit.
Output Return a toolcontextcontract containing:
Agent UX Review
Use this workflow when reviewing whether a delegated workflow can preview, pause, resume, recover, reverse, and escalate safely across real interruptions and failures.
Output Return an agentuxreview containing:
Tool Evaluation Plan
Use this workflow when designing evidence that an agent-facing product surface completes delegated work cheaply, recoverably, and safely rather than merely succeeding in a demo.
Output Return a delegatedworkevaluationplan containing:
Human review
Keep consequential decisions explicit.
These workflows structure analysis and artifacts; they do not authorize autonomous external, personnel, financial, legal, security, or other high-impact action.
Source and files
Grounded in the complete Agent-Native Tools series.
10 source essays · 4 usable skills · reviewed Jul 2026