Feedback on a review finding

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond annotations: wrong hides the finding in later reviews on this machine, right counts it as confirmed, and both teach the local learning system. It also discloses the local-file write scope, reset behavior, return format, and error conditions, which is strong transparency for a non-read-only mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded and free of filler. Each sentence carries useful information: purpose, parameter meaning, side effects, usage conditions, reset behavior, and return/error behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter mutation tool with no output schema, the description covers everything an agent needs: what it does, when to use it, what each verdict changes, where data is written, how to undo it, and what the response or error looks like.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is only 50%, the description fully explains both parameters. It clarifies that `finding` is the exact line as godot_review printed it, and it explains what each `verdict` value does, adding meaning well beyond the enum and schema example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action, resource, and effect: tell Godotwright that a godot_review finding was wrong or right. It explicitly names the related sibling godot_review and distinguishes the feedback role from code-checking siblings like godot_api and godot_check.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance: only after checking the code with godot_api or godot_check, and fix real findings instead of marking them. It also explains the consequences of each verdict, which routes the agent correctly between marking wrong versus right.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.