minimal_diff_review

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

With no annotations, the description fully discloses behavior: findings are never blocking, evidence is asymmetric (silence is not proof), confidence is labelled with specific limitations of the topology index (approximate, intra-file, possibly stale), and it degrades cleanly outside git. This exceptional transparency goes beyond typical tool descriptions.

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 a single dense paragraph, front-loaded with purpose. Every sentence earns its place, but the length and run-on structure make it slightly harder to scan quickly. It could benefit from shorter sentences or bullet-like separation, yet it remains efficient.

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?

There is no output schema, so the description carries the burden of explaining what to expect. It lists specific finding types, confidence levels, and the meaning of silence, which is substantial. It stops short of describing the exact return structure, but the behavior is well-covered for a review tool.

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 coverage is 100%, so baseline is 3. The description adds practical meaning beyond the schema by explaining `files` scoping in shared worktrees and reinforcing the default behavior of base_ref. This added context elevates the score.

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 description opens with a specific verb+resource: 'Reviews a diff for signs of over-building'. It clearly distinguishes itself from siblings by contrasting its deterministic, no-LLM approach with find_references' exact cross-file lookup. The tool's unique role as a non-blocking minimality review is unmistakable.

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?

Provides clear context: reviews working-tree diff vs base_ref, recommends passing `files` in shared worktrees, and notes graceful degradation outside git. However, it does not explicitly name when not to use it or name alternative tools for raw diffs or cross-file reference checking, leaving some inference to the agent.

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