critique_jp_ui

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

The description discloses that the tool performs static analysis and does not use screenshots, which is a meaningful behavioral trait. It also lists the specific checks it performs. However, with no annotations provided, the description carries the full burden; it doesn't disclose whether the tool modifies anything (it appears read-only), what the output format is, or whether it can handle both URL and code simultaneously. The static-analysis disclosure is useful but incomplete.

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 compact: two sentences. The first sentence states the action and resource, the second lists the specific checks and the exclusion of screenshots. It is front-loaded with the core purpose. Minor inefficiency: the list of checks could be seen as detail, but it's valuable for an agent deciding whether to invoke this tool.

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 single-parameter tool with no output schema, the description is reasonably complete: it tells the agent what input to provide and what the tool will check. However, it doesn't describe the output format (e.g., a list of issues, severity levels), which an agent might need to interpret the result. It also doesn't state whether the tool is read-only or if it requires network access for URLs. Given the tool's moderate complexity, a bit more context would be helpful.

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 schema already documents the single parameter 'url_or_code' as '点検したいURLまたはJSX/HTML'. The description adds the context that the tool accepts either a URL or code, which aligns with the parameter name. However, it doesn't add details like whether the code must be JSX/HTML specifically or whether a URL must be publicly accessible. Baseline 3 is appropriate since the schema covers the parameter fully.

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 states a specific verb ('点検します' = inspects/reviews) and a clear resource (URL string or code), and lists the specific issues it checks for (English navigation, Inter font, small text, missing furigana, missing legal links). This distinguishes it from siblings like get_jp_rules or get_jp_copy_patterns, which are retrieval tools, though it doesn't explicitly name a sibling alternative.

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 when to use it: when you have a URL or code and need a static review against Japanese UI requirements. It also states what it does NOT use ('スクリーンショットは使いません'), which is a useful exclusion. However, it doesn't explicitly contrast with sibling tools like get_jp_rules or recommend_jp, nor does it state when to prefer those alternatives.

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