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

Beyond the read-only and open-world annotations, it discloses non-exhaustive and nondeterministic results, regional playback limitations, cursor-chain constraints, and charges for repeated or empty successful requests. However, “at least 10 Nexscope credits” conflicts with “1 credit per request,” making the billing behavior unclear and preventing a top score.

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 useful purpose and return-shape information is front-loaded, but the definition then repeats its availability warning and troubleshooting link, restates its purpose several times, and includes raw pricing fragments and copied schema text. Much of the latter half is redundant or contradictory rather than earning its place.

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 seven-parameter external feed without an output schema, it supplies the main response fields, pagination workflow, completeness caveats, and recovery strategies needed to call and interpret it correctly. Its principal remaining weakness is dependable cost information, compounded by referring to an API path rather than clearly naming the corresponding sibling tool.

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?

Although the schema documents all seven parameters, the description adds valuable operational rules: keep `region` and `sort_by` fixed within a cursor chain, restart pagination after changing region, and never merge cursors from separate responses. The closing `include_pinned` paragraph merely repeats the schema and adds no further semantic value.

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 states exactly what is fetched—videos posted by a TikTok user—along with the creator-feed use case and latest/popular sorting. The later recommendation to refresh known posts through `/v2/tiktok/video` also distinguishes feed discovery from single-video lookup.

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 explicitly warns against relying on this non-exhaustive feed alone for campaign tracking and names an alternative endpoint for refreshing known URLs or IDs. It also explains when to paginate, change regions, retry pages, and deduplicate results, providing unusually actionable selection and invocation guidance.

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