Direct answerAgent evidence should answer a simple question: what independently supports the claim that the requested outcome happened? Good systems keep observations, evidence quality and final claims separate.

Evidence is not the same as a tool response

A tool response can prove that an operation was attempted or accepted. It may not prove that the intended real-world state now exists.

Match evidence to the claim

Use the strongest practical source for the task: read the resulting file, inspect the UI state, query service health, retrieve the resulting record or observe the device state.

Preserve uncertainty

If evidence is missing or contradictory, the agent should preserve that uncertainty instead of turning it into confident prose. The user benefits more from a bounded incomplete result than from false certainty.

Prefer deterministic checks where possible

Simple facts such as file existence, schema validity, counts, hashes or service status should be checked by software rather than inferred from model language.

Keep the public principle separate from implementation

Products can publish that important outcomes are independently verified without publishing their private evidence schema, state model, routing rules or recovery contracts.