review_code

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

With no annotations present, the description carries the full burden. It reveals method (Claude, whole-file reasoning, not regex), which is a non-obvious approach, and the output shape (line-referenced findings with exploit + fix). It does not mention whether it's read-only or any side effects, but for a security review that's arguably implicit.

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?

Three concise sentences pack in purpose, usage, output, and a distinguishing trait. There is zero wasted wording and the key info is front-loaded.

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?

Given the tool's moderate complexity, the description covers purpose, method, output, and usage context. It also references line-referenced findings, which aligns with likely output schema. It could mention prerequisites or size limits, but the presence of an output schema reduces the need to explain return details.

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 0%, so the description must compensate. It clearly explains the 'code' parameter as 'the file text you have open', but says nothing about the 'filename' parameter or its default. Partial coverage is provided, but one of two parameters remains undocumented.

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 function: security-reviewing a source file's contents with Claude, listing specific vulnerability categories (BOLA/BFLA/XSS/SQLi/business-logic/RCE/auth). It distinguishes itself from sibling tools by emphasizing whole-file reasoning over regex and specifying the output format (line-referenced findings with exploit + fix).

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 on when to use: 'Pass the file text you have open' implies using the tool with an open file and describes the returned findings. However, it does not explicitly mention alternative tools (e.g., review_file) or state when not to use it, so it lacks explicit exclusions.

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