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

With no annotations, the description carries the full burden and does add real behavioral context: every result carries a credibility score, Chinese queries are auto-translated, and before_chatgpt acts as a 2022-11-30 cutoff filter. It still omits return format, pagination, and any rate/auth expectations, keeping it short of a 5.

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, front-loaded sentence with a bracketed domain tag; every clause conveys distinct information (sources, credibility, cutoff semantics, translation) with no filler, though the run-on structure is slightly hard to parse.

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-annotation, no-output-schema tool the description covers what content comes back, its provenance, the credibility annotation, and the non-obvious flag semantics. Only the response shape/pagination is left unstated, which is a minor gap given no output schema exists.

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), and the description compensates by defining exactly what before_chatgpt=true does (only content before 2022-11-30) plus example query strings. It adds substantive meaning beyond the raw boolean/enum-free 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?

States a specific verb+resource (search real human-written opinions/experiences) and explicitly demarcates the content class as non-AI-generated, listing the actual sources (Taiwan reviews, PTT, HN, Stack Exchange, Lemmy). This distinguishes it from siblings like voices__get_topic_opinions and voices__check_ai_text without the agent needing to open schemas.

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?

Usage is implied by the framing (you want human opinions, not AI text), and the before_chatgpt note implies a pre-LLM-content filtering use case, but the description never states when to prefer this over get_topic_opinions or list_taiwan_posts, nor any exclusion conditions.

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