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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description does not need to restate them. It instead adds genuinely new behavior: pricing at ¥0.1 per call, billing only on success, and automatic refund on failure or empty results – material facts for a paid, open-world lookup. It does not cover rate limits or latency, keeping it short of 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 tight sentences ordered as purpose, return payload, then usage, with pricing last – front-loaded and waste-free. The return-field enumeration is the longest part but each item is load-bearing since there is no output schema.

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's return-field list is essential and present, and it discloses the commercial/billing model for a paid endpoint. The remaining gap is that it does not address what happens to private or deleted videos beyond the refund clause, which for a single read-only lookup is minor.

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 are documented, so the schema already does the work of explaining item_id and the fallback _token. The description adds no format hints for item_id (e.g., numeric vs. shortcode), 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 states a specific verb+resource ("获取TikTok视频详情") and enumerates what is returned (description, play/like/comment/share counts, author, music, publish time), so the agent knows exactly what single-item fetch this is. It does not name the sibling it is not (e.g., tiktok_post_comments or tiktok_keyword_search), relying on the reader to infer the boundary in a very crowded sibling set.

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 concrete use cases – engagement analysis of a single item, asset ingestion, or acting as the starting point for a batch task – which tells the agent when this is the right entry point. It stops short of explicit exclusions or naming the alternative tools to use instead, so the routing guidance is clear but not complete.

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