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

Goes well beyond the readOnly/openWorld annotations: discloses the empty_result behavior for non-live creators, the 1-credit cost, that no third-party provider is involved, and the caveat that `handle` can come back empty on the room_id path. These are exactly the traits an agent needs to plan a poll.

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?

Front-loaded with the resource and returned fields, followed by the behavioral notes in a logical order. Slightly dense and the opening 'Live stream info' restates the title, but no sentence is wasted.

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 carries the burden of describing return values and does so explicitly, plus cost and empty-result semantics. The gaps are `cache_max_age` meaning and what happens when both or neither identifier is passed.

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 67%, and the description compensates by explaining where `room_id` comes from (`roomId` in a prior response), which TikTok surface it targets, and the either/or relationship between `handle` and `room_id`. `cache_max_age` is left undocumented in both schema and description.

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 ('Live stream info', 'Details of a creator's stream while they are live') and enumerates the returned fields (room id, title, cover, viewers, start time), which separates it from siblings like tiktok_profile or tiktok_userVideos that cover non-live content.

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?

Gives clear usage context: it works as a cheap 'are they live?' poll because a non-live creator returns `empty_result`, and it says to pass `room_id` to hit TikTok's own webcast surface. It lacks an explicit statement of when to prefer a different tool or what happens if both identifiers are supplied.

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