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

With no annotations, the description carries the burden and does well: it discloses that each result carries a credibility score, that the corpus spans named forums, and that before_chatgpt restricts to pre-2022-11-30 content. It omits limits on result count/pagination but covers the core behavioral traits.

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 dense sentence separated by semicolons; the core purpose is front-loaded and every clause (sources, credibility, cutoff, translation) adds distinct information without filler. Dense but earns its length.

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 2-parameter, no-output-schema, no-annotation search tool, the description covers sources, credibility scoring, the cutoff flag, and translation behavior. Only minor gaps remain, such as result volume or pagination expectations.

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 only 50% (before_chatgpt has no schema description), but the description compensates by explaining that before_chatgpt=true returns only content dated before 2022-11-30, and adds that Chinese queries are auto-translated, extending beyond the schema's example-only query description.

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?

States a specific verb (搜尋) and resource (真人寫的意見與使用經驗), enumerates concrete sources (PTT, Hacker News, Stack Exchange, Lemmy) and explicitly marks the corpus as non-AI-generated. It clearly contrasts conceptually with check_ai_text, though it does not name any sibling directly.

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 for using it is implied (finding human opinions/experiences), and the before_chatgpt flag hints at a use case, but there is no explicit when-to-use vs when-not guidance or routing to alternatives like get_topic_opinions or check_ai_text.

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