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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), but the description adds real context beyond them: the exact response envelope (aweme_list with aweme_id, desc, statistics, video, author), the cursor pagination model, and a cost warning that repeated requests may re-purchase data. The cost messaging is muddled ('at least 10 Nexscope credits' versus '1 credit per request' in the appended copy), which weakens the disclosure.

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 useful content is front-loaded and well structured, but the trailing block ('TikTok TikToks using Song API View Pricing Get the TikToks using a song 1 credit per request... Examples are not guaranteed prices') is pasted supplier boilerplate that repeats and contradicts the earlier credit figure. That unmapped text wastes attention and creates ambiguity about actual cost.

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?

With no output schema, the description usefully enumerates the returned fields and explains pagination, which is enough to call the tool. However, the pricing section is internally inconsistent and there is no note on missing/empty results, rate limits, or how clipId is required in practice (required array is empty), leaving gaps for an agent deciding whether a call is affordable or valid.

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 100% and the clipId property already explains the TikTok music-URL extraction rule, so the schema carries the parameter burden. The description only adds that the cursor comes from the previous response's payload, a small but genuine addition above the schema's one-line cursor note. Baseline 3 applies.

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?

Opens with a specific verb+resource: 'Fetches TikTok videos that use a specific sound or song, identified by its clipId.' That scope is inherently different from the sibling social_tiktok_song (song metadata) and social_tiktok_search_keyword, but the description never names those alternatives, so the differentiation is implicit rather than stated.

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?

There is no when-to-use or when-not-to-use guidance and no mention of the obvious nearby alternatives (social_tiktok_song for the sound itself, social_tiktok_search_keyword for content discovery). The only procedural hint is 'Paginate with cursor from the previous response,' which is pagination mechanics rather than tool-selection guidance.

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