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

With no annotations, the description carries the full burden and does well: it discloses that a vetted human engineer performs the review, what kinds of issues are covered, and the exact output (verdict, correctness score, security findings, architecture notes, suggested changes). It also mentions the on-chain certificate for approved code, which is a notable behavioral outcome. It does not cover cost or turnaround time, but the core behavior is transparent.

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 well-structured and front-loaded, with purpose first, then usage context, then parameters, then outputs. It is denser than minimal but every sentence carries useful information, especially since there is no output schema content shown. It avoids repetition of schema field names and stays focused.

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 complexity and the lack of annotations, the description is quite complete: it explains what to pass, when to use it, and what the return value contains. It does not mention potential costs, expected turnaround time, or limitations (e.g., language support), which would be useful for a human-in-the-loop service, but it covers the essential decision-making and invocation context.

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 already provides 100% coverage of all parameters with descriptions, so the baseline is 3. The description adds a small reiteration that code can be inline or a URL and that intent should describe behavior, but it does not meaningfully expand beyond the schema. Thus no extra credit beyond the schema's completeness.

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 identifies the tool as a human code review service, specifying the resource (code) and the focus areas (correctness, security, structural soundness) beyond mere style. It distinguishes from sibling tools like review_content and review_plan by explicitly targeting code, architecture, and design decisions.

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 gives clear guidance on when to call the tool: 'before you treat code as done,' particularly for payment flows, auth, data handling, or logic where subtle bugs are costly. It does not explicitly name alternative tools or when not to use it, but the context is strong enough for an agent to select it appropriately.

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