Ad variations

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

With no annotations, the description carries the full load and does meaningful work: results land in the output directory, long jobs return a generation_id to continue via ideogram_generation, and the job is never resubmitted or billed twice. Missing are permission/enterprise nuances and any failure-mode notes, but the async/billing contract is disclosed.

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?

A single front-loaded paragraph leads with the operation and its invariant, then moves to I/O and async behavior. Nearly every clause earns its place, though the source-format list slightly duplicates the schema's own image description.

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?

There is no output schema, and the description compensates by explaining where results are saved and what a generation_id means for long jobs. For a 9-parameter, no-annotation tool this is close to sufficient; minor gaps remain around the asset-identifier path and billing for num_images (covered only in the schema).

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 already 100%, so the bar is a baseline 3, but the description adds real semantics beyond the schema: only one axis is varied while aspect ratio and product are preserved, and the image can be a file, URL, or Ideogram asset. The oneOf/required-variation_type structure is not explained, but the core parameter intent is enriched.

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 first sentence gives a specific verb (vary) and resource (an ad) plus the exact axes (people, setting, group_size, scene) and what is held constant (aspect ratio, product). That is enough to distinguish it from siblings like ideogram_ad_localizer, ideogram_ad_resizer, or the plain ideogram_generate 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 states the operative constraint up front ('vary an ad along ONE axis'), names the accepted source forms (local file, public https URL, Ideogram asset), and notes there is no price quote or dry run, which implicitly routes costing questions to ideogram_quote. It stops short of explicitly naming alternative siblings or stating when to prefer remix/edit over this tool.

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