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

With no annotations, the description carries the full burden and does substantial work: it states the data provenance (values come from TikTok), warns not to assume counts are percentages, instructs retention of source units, clarifies that missing breakdowns mean unavailable data rather than zero, and rules out pagination. It stops short of auth/permission or rate-limit context, but the interpretation caveats are the higher-value disclosure for an analytics tool.

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?

Four tight sentences, no repetition, and the most important framing (what is fetched and what it is not) comes first. Each remaining sentence carries a distinct data-interpretation constraint, so nothing is 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?

No output schema exists, so the description must pre-empt confusion about the return payload, and it does: what dimensions come back, that values are raw TikTok units, that missing data is not zero, and that there is no pagination. For a two-parameter read tool this is fully sufficient.

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%: days (enum, default 30, 'does not define the aggregation period') and query_id (what it is and what it is not) are both documented in the schema. The description adds only marginal framing via 'one search topic over a requested window,' so the baseline 3 is appropriate.

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?

Names a specific verb (fetch) and resource (TikTok country/gender/age breakdowns and demographic summaries) scoped to one search topic over a window. It then explicitly disambiguates against adjacent resources: 'not a creator's followers or a specific video's viewers,' which separates it from creator_followers, user_profile, and video_detail.

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?

States the applicable scope clearly (one search topic, requested window) and rules out the two most likely mis-selections, creator followers and video viewers. It also ties query_id back to its producers (search_topics, browse_topics, trending_topics, related_topics), though it does not give an explicit when-to-use statement or exclusions beyond those two cases.

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