Help me design the tool list for an agent.

WHAT THE AGENT DOES: [description]
SYSTEMS IT CAN REACH: [list]
THE TASK TRACE: [paste your step-by-step trace from Chapter 1]

Please:
1. Propose a tool list. For each: a name, and a description of four sentences or fewer that says what it does, when to use it, what it does NOT cover, and what it returns on failure.
2. Mark each tool as READ or WRITE. For writes, say whether the action is reversible and what the worst wrong call would do.
3. Flag any two tools that a model might confuse with each other, and rewrite their descriptions so it can't.
4. Is anything here too broad? Specifically, is there a write tool that should be split into narrower ones so we can control them separately?
5. Which tools could we cut from a first version? Aim for the smallest set that does something genuinely useful.

Agentic AI and MCP for Product Managers

Module 1What 'Agentic' Actually Means

Module 2How an Agent Actually Works

Module 3MCP: What It Is and Why You Should Care

Module 4Designing the Tool Layer

Module 5Permissions and the Human in the Loop

Module 6Evaluating Agents

Module 7Cost, Latency and Unpredictability

Module 8Designing What the User Sees

Module 9Risk and Blast Radius

Module 10When an Agent Is the Wrong Answer

Module 11Final Project: Design One Real Agent End to End

Module 12Appendix: The Prompt Library

Copy This Prompt - Designing Your Tool Inventory