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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context the annotations cannot carry: the ¥0.1 per-call price, billing only on successful calls, and automatic refund on failure or empty results — a real consideration for an agent deciding whether to retry. It omits return-format detail such as null handling for missing metrics, which keeps it from a 5.

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?

Three front-loaded sentences: what it returns, when to use it, then cost. The field enumeration is dense but each item is a real return value an agent needs, and the billing caveat is short. No filler or restatement of the tool name.

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 present, the description takes on the burden of describing return values and does so explicitly, listing every field family returned. Combined with annotations covering the safety profile and a complete parameter schema, an agent has enough to invoke this correctly; only the provenance of aweme_id is a minor gap.

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% for both parameters, so aweme_id and the fallback _token are already documented structurally, establishing the baseline of 3. The description adds no meaning beyond the schema — notably it never says where an aweme_id comes from (e.g., a keyword-search result) or what format it takes, which would have been the highest-value addition.

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 and resource (获取抖音视频详细信息) and enumerates the returned fields — caption, like/comment/favorite/share counts, author nickname plus sec_uid, publish time, cover, BGM — so the agent knows exactly what comes back. It does not explicitly differentiate from overlapping siblings such as douyin_video_like_count and douyin_video_play_count, which also surface engagement numbers, so the boundary is inferred 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?

Gives three concrete usage contexts: single-item engagement analysis, material archiving, and acting as the entry point for a batch job — the last one meaningfully hints at chaining with comment or batch tools. It stops short of naming an alternative tool or a when-not-to-use condition, so it is clear context without exclusions.

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