Headline variants of a static ad

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

Annotations are all false flags and provide little operational context, so the description carries the full burden. It discloses pricing mechanics (3 credits for text read + one image edit per headline), upfront batch pricing, proofreading with textCheck flags, never silently re-rendering, brand-voice generation, and refusal to invent numbers or claims. This is rich behavioral disclosure well beyond the annotations.

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 description is front-loaded with the core scope and then packs pricing, safety constraints, proofreading behavior, and return values into a few dense sentences. Every sentence adds operational value; none repeats schema content verbatim or pads with filler. The structure lets an agent quickly grasp both purpose and call semantics.

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?

Despite having no output schema, the description states what is returned (each headline, its angle, and its image URL) and covers constraints, pricing, and validation behavior. An agent has enough context to invoke the tool correctly and anticipate outcomes. The only notable omission is explicit sibling alternatives, which was already accounted for under usage guidelines.

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 meaning beyond the schema: the either/or relationship between `headlines` and `count`, the default and max behavior, the purpose of `brief`, and that generated headlines follow the saved brand's voice. This helps an agent choose and combine parameters correctly, though it doesn't override the schema's own solid 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?

Description opens with a specific verb and resource: turning ONE finished static ad into copies that differ ONLY in the headline for an A/B test. It clearly distinguishes itself from generic ad-editing or remixing tools by locking scope to headline-only variation while preserving all other elements. The phrase 'same picture, product, layout, colours and every other line' makes the tool's specialized role unmistakable.

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?

The description clearly states when to use the tool: when you have a finished static ad and want headline-only A/B test variants. It gives context like the ability to provide your own headlines or have them written, and what `brief` steers. However, it does not explicitly name alternative sibling tools (e.g., remix_static or multiply_ad) or state when NOT to use it, so it misses full exclusionary guidance.

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