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

With no annotations, the description carries the disclosure burden and does well: it states the credit cost (3 credits, cached or not) and that failed calls are refunded, which an agent cannot infer elsewhere. Read-only nature and the cache-bypass behavior of `fresh` are only implied or relegated to the schema.

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?

Two sentences with the core resource and return fields front-loaded, followed by the selection constraint and cost note. The long field enumeration is dense but each item helps the agent judge relevance.

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 no output schema, listing the returned fields is the right compensation, and pagination is fully covered by the schema's cursor/limit descriptions. Cost and refund behavior round it out; only the relative positioning against get_tiktok_video/search_tiktok is missing.

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, but the description adds the mutual-exclusivity rule for `username` and `url` ('Give exactly one of'), which the schema does not encode. That is genuine added meaning beyond the parameter descriptions.

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 and resource ('Fetch recent videos by one TikTok account') and enumerates the returned fields, making clear this returns a collection rather than a single item. It does not explicitly name the sibling get_tiktok_video or search_tiktok, so the differentiation from those tools is left implicit.

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?

Usage is only implied: 'recent videos by one TikTok account' tells the agent the context, and 'Give exactly one of `username` or `url`' is a useful selection constraint absent from the schema. However, there is no explicit when-to-use vs. when-not, and no alternative tool is named.

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