Review a diff

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavior beyond that: omitted base resolves from origin/HEAD, and the report tail spills into a brain://payload resource when it exceeds the inline budget. That truncation/resource behavior is exactly the kind of non-obvious detail that helps an agent handle the response.

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?

Two short sentences, front-loaded with the core action and the base default. The doubled backtick markup around brain://payload is slightly noisy but costs almost nothing in length.

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?

With no output schema, the description must carry the return contract; it partially does by disclosing where an oversized report goes, but it says nothing about the report's format or content, and the head/repo_path semantics are absent for a 0%-coverage schema.

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?

Schema description coverage is 0% and the schema gives only titles and defaults. The description explains base's default resolution, but head (default 'current') and repo_path receive no explanation in either place, leaving two of three parameters semantically undefined.

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?

The phrase 'Review changes' names a verb and object, and the name review_diff makes the diff context clear, but the description never says what kind of review occurs (static analysis, LLM critique, lint) or what 'changes' spans. It does not differentiate itself from any sibling; record_* siblings are unrelated but nothing here routes the agent.

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?

No when-to-use guidance, no prerequisites, no alternatives named. The only contextual cue is a default-resolution note, which is parameter behavior rather than usage guidance.

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