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

Goes beyond the readOnly/openWorld annotations by disclosing that For You is sampled 'as a neutral US viewer' (a geo/personalization caveat an agent cannot infer) and that results are a sample rather than a ranking. Limit-cap lowering is already handled in the schema, so the remaining gap is minor.

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 short sentences plus a concrete example, with the most decision-relevant fact ('Samples, not rankings') front-loaded. No filler.

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 full schema coverage, rich annotations, and an output schema, the description only needs to cover intent and sampling semantics, which it does. Minor omission: no mention that the different methods have different page-size ceilings (that lives only in the schema).

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 100%, so the baseline is 3; the description adds an example invocation ({'method':'explore','category_id':3}) and reiterates where category_id values originate, which links parameters across tools rather than restating field docs.

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 ('samples') and resource ('TikTok's own feeds') and enumerates the three feed families: For You, Explore categories, and Discover (creators/hashtags/sounds). 'Samples, not rankings' plus 'TikTok's own feeds' cleanly separates it from sibling search tools (video_search, hashtag_search) and ranking tools (video_top_selling).

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 a prerequisite dependency — category ids come from reference method=explore_categories — which is genuinely useful routing information. However, it never states when to prefer this over video_search or video_top_selling; the distinction is only implied by the word 'samples'.

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