review_code

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

With no annotations, the description fully explains behavior: it analyzes for bugs, security issues, and violations, and returns findings with severity, explanation, and fixes. It does not mention side effects or permissions, but these are not needed for a read-only analysis. Transparent enough for an AI agent.

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 concise sentences: first states purpose and returns, second states input format. No unnecessary words. Front-loaded with key action and result.

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 tool has only 2 parameters (1 required) and no output schema. The description explains what it returns (findings with severity, explanation, fixes). This is sufficient for an agent to use it correctly without further detail.

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?

The input schema covers both parameters with descriptions that match the tool description. The description adds no new information beyond what the schema provides (e.g., 'diff' is already described as unified diff). Schema description coverage is 100%, so baseline 3 is appropriate.

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 that the tool reviews code changes for bugs, security issues, and best practice violations. It uses a specific verb ('review') and identifies the resource ('code changes'). It distinguishes itself from sibling tools like 'fix_code' (which fixes) and 'ask_codepeel' (likely for questions).

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 provides explicit guidance on input format: 'Pass a unified diff or file contents.' It implies this is for reviewing changes before merging, but does not explicitly exclude other scenarios or mention when to use alternatives. Clear context with room for more precision.

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