---
title: "Comment by Adam Lewis on \"A Tool Result Is Evidence, Not Ground Truth\" | Hashnode"
description: "The valid-JSON-but-wrong case is the one that worries me with agents, because everything downstream treats parsed as true. I keep a verification step in the wor"
url: "https://hashnode.com/posts/a-tool-result-is-evidence-not-ground-truth/6a94bd1b37a23da4b7a5a41e/comment/6a97f18ba237dafb1fa12440"
---

[Discussion](https://hashnode.com/posts/a-tool-result-is-evidence-not-ground-truth/6a94bd1b37a23da4b7a5a41e)

Comment [A Tool Result Is Evidence, Not Ground Truth](https://hashnode.com/posts/a-tool-result-is-evidence-not-ground-truth/6a94bd1b37a23da4b7a5a41e)

[Adam Lewis](https://hashnode.com/@nark3d)

[Sep 2](https://hashnode.com/posts/a-tool-result-is-evidence-not-ground-truth/6a94bd1b37a23da4b7a5a41e/comment/6a97f18ba237dafb1fa12440)

The valid-JSON-but-wrong case is the one that worries me with agents, because everything downstream treats parsed as true. I keep a verification step in the workflow itself, so the agent has to run the check or quote the source before a result gets used, whichever tool produced it. The MemToC numbers are better evidence for that habit than I had before.
