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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description does add two things not in annotations: the shape of the return value (a `suggestions` array) and cost behavior, including that repeat requests re-purchase data. That cost disclosure is genuinely useful. It is undercut by self-contradicting figures — 'at least 10 Nexscope credits' followed by '1 credit per request' — which leaves the agent unable to reason about budget.

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 definition is bloated with pasted pricing-page artifacts — 'TikTok Search Suggestions API View Pricing', 'Actual supplier units are reported per request. Examples are not guaranteed prices.' The purpose statement is duplicated almost word for word, and the two credit figures conflict. Front-loading is fine, but several sentences do not earn their place and one actively misleads.

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?

For a simple two-parameter read tool with no output schema, the description does tell the agent it returns a `suggestions` array, which compensates for the missing output schema. What is missing is any positioning against the crowded set of TikTok and SEO search siblings, and any hint about what `region` affects. Adequate but with clear gaps.

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 `query` and `region` are already documented in the schema. The description mentions 'for a query' but adds no format, length or region-code conventions beyond the schema text, and never mentions `region` at all. Baseline 3 applies since the schema carries the weight.

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 opening sentence gives a specific verb and resource: retrieves the autocomplete suggestions TikTok surfaces while a user types in search. That is concrete and unambiguous. However it never distinguishes itself from near-identical siblings such as social_tiktok_search_keyword, social_tiktok_search_top or social_seo_search_autocomplete, and the purpose sentence is then repeated verbatim later in the text.

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?

There is no guidance on when to reach for this tool versus the other TikTok search endpoints or the generic autocomplete tool. The only implicit signal is 'autocomplete', which requires the agent to infer the use case. No prerequisites, no exclusions, no alternatives named.

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