review_diff

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

Without annotations, the description carries full burden. It clearly states a key behavioral trait: 'Only findings on lines the diff adds are returned,' which defines scope. It does not mention mutation or destructive effects, which is acceptable for a read-only analysis tool.

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—three sentences that front-load the purpose. Every sentence adds value with no wasted words, making it easy to parse.

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 only one parameter and no output schema, the description covers the key aspects: input format, scope (only added lines), and use case. It could mention return format or error conditions, but it is largely sufficient for an agent to understand how to invoke the 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?

The input schema provides no description for the 'diff' parameter (coverage 0%). The description compensates fully by specifying it expects a unified diff (e.g., from git diff) with file paths relative to the current project directory, adding essential meaning beyond the schema.

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: 'Security-review a unified diff: flag issues the change *introduces*.' It specifies a specific verb (security-review) and resource (unified diff), distinguishing it from sibling tools like secure_pattern or security_scan which likely focus on different aspects of security analysis.

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 context for when to use the tool: 'after editing Kotlin code' and 'a self-check before committing.' It implies the tool is for reviewing one's own changes, though it does not explicitly exclude alternatives or explain when to use sibling tools.

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