Claude Review Diff

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

Given no annotations, the description carries full burden. It clearly states that the tool runs read-only git commands and that Claude never modifies anything. It also discloses behavioral traits such as the 'deep' depth mode being slower and higher usage. However, it does not mention error handling or performance limits.

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 concise and well-structured, front-loading the primary purpose and then elaborating on key parameters and usage context. Every sentence adds value, with no redundancy.

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?

While the description covers usage well and mentions the result footer for session continuation, it does not explicitly describe the output format (e.g., what the review looks like) since no output schema exists. A bit more detail on the output would improve completeness.

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 100%, so baseline is 3. The description adds context about default behavior and the purpose of the 'base' parameter, but does not significantly enhance understanding beyond what the schema already provides for each parameter.

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 clearly states the tool's purpose: reviewing actual code changes via read-only git operations. It specifies the verb 'review', the resource 'code changes', and distinguishes from the sibling tool 'claude_review_files' by noting that this tool requires git context.

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?

Explicitly mentions when to use ('after implementing something'), explains default behavior (review uncommitted changes against HEAD), describes how to use the 'base' parameter for comparing against a ref, and recommends an alternative tool for non-git reviews. Also states that Claude only advises and never modifies anything.

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