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

Annotations only mark it as destructive and open-world; the description adds the financially material behavior an agent cannot infer: credits are charged per image, failed generations are refunded, and the image link is normally returned in the same call. It also discloses the 10-minute dedupe window that silently returns the prior result, which materially affects repeat-call behavior beyond idempotentHint=false.

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?

Purpose is front-loaded in sentence one, followed by cost/return behavior, then a numbered pre-call checklist. The only near-redundancy is the public-figure warning echoing the consent rule, which is defensible given the safety stakes.

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 10-parameter, credit-spending, destructive tool with an output schema, this covers prerequisites, cost, safety, and dedupe. The one gap is 'usually returns the finished image link' — the agent is not told what to do in the non-usual case (poll get_run or get_creation).

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, and the description still adds real meaning: the photos-vs-photoUrls choice with format constraints, that 'count' multiplies the credit charge, and that requestId is the lever for deliberately regenerating. It stops short of explaining resolution/aspect trade-offs or the photosConsent default, leaving those to the schema.

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 concrete verb and resource ('Make AI images from the user's prompt') and enumerates the three modes: text-to-image, photo editing, and photo combining. It also names the model family (MakeViral Create) and the sibling tool get_model that provides model metadata, so an agent can place it precisely among the siblings.

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?

Gives an explicit pre-call sequence (pick model via get_model, quote the credit price, obtain consent when photos are involved) plus prohibition rules (no public figures, no non-consenting people, no children). It also explains the alternatives for supplying images ('photos' attachments vs 'photoUrls' public links) and when to supply a new requestId.

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