Review-Code

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool builds prompts for review and scoring, but doesn't describe what the prompts look like, how they're structured, or any behavioral traits (e.g., whether it's idempotent, requires specific inputs, or has side effects). The mention of '不直接调用 LLM' hints at a non-execution role, but this is insufficient for a tool with 3 parameters and no annotation coverage.

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 extremely concise—a single sentence in Chinese that efficiently states the purpose and a key constraint ('不直接调用 LLM'). It's front-loaded with the main action and wastes no words. Every part of the sentence earns its place by clarifying the tool's role.

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 complexity (3 parameters, 0% schema coverage, no annotations, no output schema), the description is incomplete. It explains the high-level purpose but fails to address parameter meanings, behavioral details, or output expectations. For a tool that likely generates structured prompts, more context is needed to guide effective use.

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 0%, meaning none of the 3 parameters ('diff', 'style', 'commitMessage') are documented in the schema. The description adds no information about these parameters—it doesn't explain what 'diff' should contain, what 'style' refers to, or how 'commitMessage' is used. With 0% coverage and no compensation in the description, this is a significant gap.

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: '构建用于 Git diff 变更审查与打分的 LLM 提示词' (builds LLM prompts for Git diff change review and scoring). It specifies the verb ('构建' - build), resource ('LLM 提示词' - LLM prompts), and scope ('Git diff 变更审查与打分' - Git diff change review and scoring). However, it doesn't explicitly differentiate from sibling tools like 'review_code' or 'review_file', which likely have overlapping purposes.

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 minimal guidance: it mentions '不直接调用 LLM' (does not directly call LLM), which implies this tool generates prompts rather than executing them. However, it offers no explicit when-to-use instructions, no alternatives (e.g., when to use 'review_code' instead), and no prerequisites. The context is vague, leaving the agent to infer usage scenarios.

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