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

No annotations are provided, so the description carries the disclosure burden. It usefully reveals the data's provenance signals (human verification, AI-text labeling, reader voting), which is real behavioral context. However it omits any pagination/ordering behavior and confirms read-only only implicitly through 列出.

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 compact sentence front-loaded with the bracketed site tag and the core verb+resource, followed by feature and filter qualifiers. No filler, though the bracketed tag is slightly decorative.

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 no-annotation, no-output-schema list tool it conveys purpose, data traits, and two filters adequately. Still missing: how query interacts with topic, result ordering/pagination, and any sense of result size, which an agent would need to call it confidently.

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% across three parameters, so the description must compensate. It partially does: 主題 maps to topic and 只看像真人的 maps to human_only, adding semantic intent. The query parameter is never mentioned, leaving one of three params undocumented anywhere.

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 and resource: 列出 (list) 台灣真人使用心得 (Taiwan human-submitted usage reviews), with parenthetical qualifiers describing the data. It is clear on its own, but does not distinguish itself from siblings like voices__search_human_opinions or voices__get_topic_opinions, so sibling differentiation is left to inference.

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 clause 可篩主題與只看像真人的 implies usage (filter by topic, restrict to human-looking posts), but there is no explicit statement of when to use this list endpoint versus the search/get siblings, nor any exclusion guidance. Usage is only implied.

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