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

Beyond the annotations (readOnlyHint, openWorldHint), the description discloses the 60-comment cap, that results are in TikTok's own ranking order, that replies are excluded, that unknown/deleted video IDs return an empty list with total 0, and even the billing model ($0.002 per successful call via x402, failures uncharged). That is exactly the extra behavioral context annotations cannot carry.

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 core capability is front-loaded in one dense sentence, followed by limits and then alternatives. The 'Related tools' clause reads awkwardly and repetitively ('when you need X ... : the top-performing TikTok'), and the payment sentence is long, but nothing is wasted overall.

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 read tool with an output schema, this covers everything an agent needs: input forms, cap and default, ordering, absence of replies, empty-result behavior for bad IDs, sibling routing, and cost. No question remains before calling it.

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 100%, so both 'url' (URL or numeric ID) and 'limit' (1–60, default 20) are already fully documented. The description only adds that the ceiling is 60 and that ordering follows TikTok's ranking, which is marginal value over the schema — baseline 3.

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 ('Top-level comments of a public TikTok video') and immediately scopes what is returned and what is not ('no reply threads', 'TikTok's own ranking order'). It also names two sibling tools so the agent can tell it apart from social_tiktok_creative_center_top_ads and social_tiktok_hashtag_analytics without opening any schema.

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 gives clear when-to-use guidance for the two named alternatives ('when you need TikTok Creative Center Top Ads', 'when you need TikTok hashtag stats'), plus an explicit exclusion of reply threads. The gap is that the closest siblings — social_tiktok and social_tiktok_profile — are never addressed, so the agent must infer the boundary against those itself.

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