review

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

Beyond readOnlyHint the description discloses the default input source (git diff against HEAD plus new files), the default lens set, the default low thinking budget, and that findings are UNVERIFIED and may be false positives with instructions to confirm and report rejections. This is exactly the operational context annotations cannot carry.

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?

Purpose, applicability, defaults, parameters and the verification caveat arrive in that order with no filler. The per-parameter lines are terse and each conveys a default or a decision the caller must make.

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 an output schema present, the description need not explain return values, and everything else an agent needs is covered: when to call, what gets reviewed by default, how to override inputs, how to bound cost via lenses/thinking, and how to treat the output. Nothing material is missing for a 7-parameter 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 description coverage is 0%, so the description carries the full burden and does: focus, diff, base (with a 'main' example), paths, lenses (with the actual default list), thinking (with default and 'high'/'max' meaning), and project_dir with a narrowing condition. Each of the 7 parameters is explained in terms of intent, not just type.

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 first sentence names the operation ('review'), the mechanism ('independent cheap reviewers... one per lens, in parallel') and the object ('a change'). That mechanism is distinct from siblings like investigate, consult and delegate, so the agent can tell them apart without further reading.

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?

It gives an explicit when ('risky or large changes') and when-not ('not routine ones whose tests pass'), which is stronger than most definitions. It stops short of naming alternative tools, so the agent must infer that routine work should skip this and use nothing or a lighter sibling.

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