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

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing billing behavior (flat $0.002 per successful call, any limit up to 50), error handling (errors are not charged), the free-trial window (first success per client IP per 30 days, signalled by X-ScrapeMole-Free-Trial: 1), and what happens on later calls (402 with a PaymentRequired object). This is exactly the operational context annotations cannot carry.

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 use case and return payload are front-loaded, and the free-trial mechanic follows logically. There is some redundancy, though: the $0.002 price and the paid-call behavior appear twice, and the free-trial and paid flows could be merged into one tighter sentence.

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 paid, no-output-schema tool it covers what's needed: the returned field set, the 50-item ceiling, filter dimensions, billing, error non-charging, and the exact 402/free-trial handshake. Minor gaps remain around response shape details (e.g., what a 402 body contains beyond the mention of PaymentRequired) and whether the trial flag appears on every response.

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 a 3 is the baseline, but the description adds real meaning: the optional filters correspond to sort order, upload date and duration, and pricing is flat regardless of the limit chosen up to 50. That clarifies the practical cost implication of the limit parameter, which the schema does not state.

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 ('find YouTube videos for a query') and lists the returned fields and filter dimensions, so the agent knows exactly what it gets. It does reference the paid endpoint '/v1/youtube/search', but never names the sibling tool youtube_search or states how the free-trial call differs operationally from it, so sibling differentiation is only implied.

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?

'Use when you need to find YouTube videos for a query, e.g. competitor or trend research' gives a concrete usage context, and the payment mechanics ('call with a query and no payment header') tell the agent precisely how to invoke the free trial. It stops short of explicit routing rules, such as 'after the trial is consumed, use youtube_search instead'.

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