deepseek_code_review

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

With no annotations, the description carries the full disclosure burden. It does openly state that code is sent to DeepSeek and that analysis is returned, which is the core behavior. However, it omits important context for a tool that transmits source code: no mention of privacy/data-handling implications, auth requirements, response format, or whether the call is synchronous. These are meaningful gaps.

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?

A single, front-loaded sentence states the action and the concrete review areas without fluff. Every clause contributes essential information (send, target, analysis categories), making it appropriately sized and easy to scan.

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?

For a simple stateless tool, the description plus fully-documented schema is enough to invoke it correctly: provide code, optionally language and deepthink, and expect an analysis. There is no output schema, so the described return content ('potential bugs, performance issues, and improvement suggestions') covers the response. Minor incompleteness from missing sibling differentiation and response format is already accounted for in other dimensions, so this dimension remains adequate.

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 100%, so the baseline is 3; the schema already documents 'code', 'language', and 'deepthink' adequately. The tool description adds no additional meaning or usage detail for these parameters, so no reason to exceed the baseline.

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 action ('Send code to DeepSeek for review') and the deliverable ('analysis of potential bugs, performance issues, and improvement suggestions'). It is a specific verb+ressource+output combination. However, it does not explicitly distinguish itself from siblings like deepseek_debug or deepseek_explain, so it falls short of a 5.

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 context of when to use this tool is implied: an agent would use it when code review is needed. But there is no explicit guidance on when to prefer this over deepseek_debug, deepseek_explain, or deepseek_evaluate_idea, and no 'when not to use' conditions. This leaves the choice to inference.

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