---
title: "Comment by indiainfranotes on \"Your MCP tools never told the agent what they can do\" | Hashnode"
description: "The annotation is the permission model, not a docstring. If the tool description is missing, the agent will guess the argument shape and the server will accept"
url: "https://hashnode.com/posts/hintgap/6ac4697480b08887654a344e/comment/6ac49f91b5def79c787efdc5"
---

[Discussion](https://hashnode.com/posts/hintgap/6ac4697480b08887654a344e)

Comment [Your MCP tools never told the agent what they can do](https://hashnode.com/posts/hintgap/6ac4697480b08887654a344e)

[indiainfranotes](https://hashnode.com/@indiainfranotes)

[Oct 6](https://hashnode.com/posts/hintgap/6ac4697480b08887654a344e/comment/6ac49f91b5def79c787efdc5)

The annotation is the permission model, not a docstring. If the tool description is missing, the agent will guess the argument shape and the server will accept a wider call than the human would. Are the tool descriptions treated as sensitive data, or as public schema? Which one do you log when the agent picks the wrong tool?

iin1006h12

[JAY TANK](https://hashnode.com/@jaytank)

[Oct 7](https://hashnode.com/posts/hintgap/6ac4697480b08887654a344e/comment/6ac49f91b5def79c787efdc5#reply-6ac5bce5794e021d8ca708c5)

That's the exact framing behind hintgap - the annotation is the permission model, not documentation. If destructiveHint/readOnlyHint is missing, the agent reasons about blast radius from the name and description alone, and a vague description invites precisely the "guess the argument shape, server accepts a wider call" failure you describe.

On your two questions:

Sensitive or public schema? It's public schema - the description/annotation ships to any client that lists your tools, so it must never carry secrets, internal hostnames, or auth hints. But it's security-relevant public schema: it defines what the agent believes it's allowed to do, so it deserves review like an authz policy, not a changelog.

What to log when the agent picks the wrong tool? The decision context, not the payload: the tool name chosen, which annotations were present/absent at call time, and the shape of the arguments (keys/types, not values). That tells you whether the miss was a missing hint, an ambiguous description, or a genuine model error - which is exactly the signal you feed back into tightening the schema.
