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

The annotations already establish a read-only, idempotent, non-destructive, open-world read, so the safety profile is covered elsewhere. The description contributes genuinely new behavioral context: per-call pricing of ¥0.1 with billing only on success and auto-refund on failure or empty results, plus the platform visibility limit on pagination depth. It omits rate-limit and authentication context, which keeps it below the top score.

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 front-loaded with the operation and its return fields, then moves to use cases, then commercial and platform constraints; every sentence carries information. It is compact for the amount of ground it covers, with only minor redundancy between the field list and the use-case clause.

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?

Because no output schema exists, the description correctly enumerates the payload fields an agent needs in order to judge fitness. Pricing, refund rules and the pagination ceiling round out what a caller must know before spending money on a loop of calls. The missing piece is a pointer to how to obtain item_id and how to page with cursor, which would make it fully self-sufficient.

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?

The schema description coverage is 100%, and the schema already documents count, cursor, item_id and the _token fallback, so the schema carries the burden of explaining parameters. The description adds only a general note that results are paginated ("按页返回") without linking it to the cursor or count parameters or explaining page sizing. The baseline score of 3 is therefore appropriate.

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 and resource ("获取TikTok视频评论") and enumerates the returned fields (comment text, like count, reply count, commenter nickname/region, timestamp), which is more than a restatement of the name. It stops short of naming the sibling tiktok_sub_comments as the place to go for replies, even though it advertises a reply count, so the boundary between this tool and that sibling is left implicit.

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?

It lists three concrete scenarios (sentiment analysis, competitor reputation comparison, public-opinion monitoring), so the intended use is clearly implied. However, there is no guidance on where item_id comes from (e.g. tiktok_post_detail or tiktok_keyword_search), and no statement about when to prefer this tool over tiktok_sub_comments for reply threads; those omissions keep usage guidance at a minimum-viable level.

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