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

Beyond the readOnlyHint/openWorldHint annotations, it discloses that a room-access refusal yields HTTP 403 with no credit charge, that audience controls can suppress a room without the profile being deleted, and that other upstream failures remain errors rather than empty results — genuinely useful behavioral context. However, its cost disclosure is self-contradictory ('at least 10 Nexscope credits' versus '1 credit per request'), which blunts the value of the pricing information.

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 description is duplicated verbatim, and a chunk of marketing/boilerplate ('TikTok Live Info API View Pricing Gets info for a TikTok live room... 1 credit per request') is pasted mid-paragraph, breaking the flow. The genuinely useful prerequisites and error semantics are buried between the duplicated block and the pricing noise, so the agent must parse redundant text to reach the front-loaded guidance.

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 compensates by enumerating the returned fields (room_id, like_count, viewer_count, status, title, cover_url, owner) and by covering the 403/error distinction and prerequisite chain. The only gap is the inconsistent credit accounting, which leaves the agent unsure of the real cost of a call.

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 both parameters (room_id, user_id) are already documented in the schema with their exact source paths. The description restates the same provenance guidance at the endpoint level, adding sequencing context but no new meaning about formats or constraints, so the 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?

The description opens with a specific verb and resource ('Gets curated room-level info for a TikTok live from TikTok's public live-room source') and explicitly separates itself from the sibling `/v1/tiktok/user/live` endpoint, explaining the different upstream call and smaller payload. An agent can distinguish this from social_tiktok_user_live and social_tiktok_livestream_analytics without opening a 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 prescribes an explicit call ordering: use `/v1/tiktok/user/live` first to obtain `room_id`, and `/v1/tiktok/profile` first to obtain `user.id` when only a handle is known. It also tells the agent when a 403 is NOT an error condition, which is the main mis-invocation risk for this tool.

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