review_code

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It clearly states that the tool does not call an LLM directly (it '不直接调用 LLM'), which is a key behavioral trait. However, it does not disclose what the output looks like, whether it requires specific permissions, or if it has side effects (e.g., saving prompts). For a tool that builds prompts, return format and any side effects are important for agent transparency.

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 a single sentence that efficiently communicates the core purpose and a critical behavioral constraint. It is front-loaded and contains no extraneous information. It earns its place by being both concise and informative.

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 builds a prompt for code review, the description is fairly complete: it says what it does (generate a prompt) and what it does NOT do (call an LLM). However, with no output schema and no behavioral transparency about return values or side effects, the agent may not know what to expect from the output. The sibling tools suggest 'parse_review_score' consumes this output, but the description doesn't confirm that. A slightly longer description explaining output format would improve completeness.

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 100%, so the baseline is 3. The description adds no additional meaning beyond the schema: parameter names and their descriptions in the schema already cover the three parameters (code, style, commitMessage). The description does not clarify how 'code' should be formatted, how 'style' affects the generated prompt, or what 'commitMessage' does. It adds marginal value over 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 verb ('构建','generate') and resource ('LLM 提示词','LLM prompt') for code review and scoring. It also distinguishes itself by noting it does NOT call an LLM directly, which differentiates it from the sibling tools 'review_diff' and 'review_file' that likely perform actual code review. However, the description is in Chinese, which may limit understanding for non-Chinese-speaking agents, but it still conveys purpose effectively.

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 implies usage for building a prompt for code review, but it lacks explicit guidance on when to use this tool vs alternatives like 'review_diff' or 'review_file'. It does not state when NOT to use it, nor provide context about prerequisites or integration with other tools like 'parse_review_score'. The sibling tools suggest a workflow, but the description doesn't clarify the role of this tool within it.

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