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

Beyond the supplied annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses genuinely useful behavior: asynchronous background execution, status-by-replay polling, email delivery of the result, and per-file billing of roughly $1–$2. The only soft spot is that 'the same request again returns its progress' sits in mild tension with idempotentHint=false, since an agent could read it as a free safe retry; it is a nuance rather than a direct contradiction.

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 main action is front-loaded in the first clause and the remaining sentences are compact parameter hints with no filler. It reads as a slightly run-on block rather than a structured list, which costs a little scannability but wastes no words.

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 costly, asynchronous, side-effecting tool with no output schema and an opaque five-parameter schema, the description covers the essentials (async, polling, email, cost) but leaves gaps an agent needs: what the emailed result contains, what 'every' controls, and where to look for valid model names (a list_models sibling exists). Adequate but not complete.

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?

With 0% schema description coverage, five parameters, and bare titles like 'Every' and 'Image', the description has to carry the load and only partly does: it maps product ('the product and the offer'), image/image_link ('the product's photo'), and model ('the video model, default a low-cost one'). The 'every' parameter is left completely unexplained, and the accepted form of image vs image_link (URL string vs object) and the available model values are not clarified.

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 names a concrete verb and resource ('turns one product photo into an ad pack') and enumerates the pack's contents — ad picture with headline, short video, voice-over, music, delivered by email. That composition makes it distinguishable from generic media siblings such as make_media or trend_to_video without opening any schema.

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 gives clearly usable operating context: the work happens in the background, and 'the same request again returns its progress or the finished result', which tells the agent how to poll. It also states cost per file (~$1–$2). It stops short of naming when to prefer it over make_media or trend_to_video, or stating any exclusion, so it does not reach the top band.

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