Agent docs: making people trust it

Your first line in any agent design is what the agent must not do. Most failures come from unclear scope, sloppy tool contracts and missing failure handling, not from a weak model.

Task: The team built an agent and nobody knows what it can and cannot do.

[Before you start, do three things]
1. Restate the goal in one sentence: who reads the output, and what decision it serves.
2. If I have not given you the following, ask me. Do not assume:
   - the task list it handles
   - known failure modes
   - steps needing human confirmation
   - how data is used
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- first paragraph: what it is good for and what it is not
- three real usage examples with expected output
- state known limitations and error types
- say how long data is kept and who can see it

[Process]
1. Write the boundary: what it may do, must never do, and when to hand back to a human
2. Define each tool's inputs, outputs, failure semantics, idempotency
3. Write the flow as a state machine with exit conditions
4. Design failure paths: retry, degrade, abort, escalate
5. Give one testable success criterion

[Output]
Fixed shape: boundary, tool contracts, state machine, failure paths, criteria.

[Do not]
- No general-purpose agent that does everything
- Never let fuzzy prose stand in for a tool contract
- The agent must not decide whether approval is needed
- No 'do your best' instead of an abort condition