The words and hashtags inside the brand’s TikTok mentions

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

Annotations already declare readOnlyHint and openWorldHint, and the description reinforces that with 'Read-only, free.' It adds the authorization requirement (brand-insights permission) and the counting scope (top 1,000 posts over 90 days). It also explains the two-endpoint behavior and that BOTH makes two calls—useful context beyond the schema. No contradiction with annotations.

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?

The description is a single paragraph with several dense sentences, but each adds value: purpose, distinction from alternatives, endpoint behavior, counting scope, preconditions, and authorization. It's front-loaded with the purpose and avoids fluff. Minor inefficiency: some redundancy with annotations (read-only) but acceptable for completeness.

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, so the description must explain return values—it does (top 20 each). It covers the business-account precondition, authorization, counting scope, and endpoint selection. It doesn't mention pagination or error cases, but for a simple read-only analytics tool, the essential information is present. The two-endpoint complexity is well explained.

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 both parameters are documented in the schema. The description adds meaning by explaining that kind:'KEYWORDS' or 'HASHTAGS' calls only one endpoint, while BOTH makes two calls, and that regions narrows which posts are counted. This is helpful but not essential, given the schema already describes the parameters adequately. 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?

The description states precisely what the tool returns: top 20 keywords and top 20 hashtags from captions of mentioning posts. It clearly distinguishes this from sibling tools by explaining it answers 'what people say' rather than 'which posts', and notes the two-endpoint nature. The verb and resource are unambiguous.

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 explains the distinction from post-level tools and notes the business-account precondition common to mentions tools. It doesn't explicitly name alternatives or state when NOT to use it, but the context is clear that this is for language analysis, not post enumeration. The kind parameter guidance is also present.

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