review

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

The description discloses that the tool is read-only and never writes to disk, which is critical behavioral information. It also describes the return value structure. However, with no annotations provided, it could further detail potential side effects or limitations such as token consumption or error handling.

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 at approximately 150 words, with the core purpose in the first sentence. It efficiently covers usage, alternatives, safety, and return format without redundant information.

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?

The description is fully self-contained for a tool with no output schema, providing the return object structure. It covers purpose, usage guidelines, parameter semantics, behavioral transparency (read-only), and alternatives, making it complete for an agent to understand and invoke the tool correctly.

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 75%, and the description adds meaning by explaining the role of each parameter (e.g., 'Pass the code itself in `content`'). It also describes the default for review_type and the overall return structure. This adds value beyond the schema alone.

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 reviews a code blob in context and returns structured findings, quality score, and suggestions. It distinguishes from sibling tools by explicitly naming analyze_file and council as alternatives for different scenarios, and specifies that it does not read files from disk.

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?

The description explicitly states when to use this tool (when Claude already has the code in hand) and when not to use it (for files not seen, use analyze_file; for multiple perspectives, use council). It provides clear usage context and alternatives.

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