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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing concrete credit prices per image for each action, that the call always returns status='confirmation_required' with an action_id and plan_token, that the write only happens via confirm_action, and that the new order_id should be polled with creative_get. This is exactly the behavioral context a mutating, credit-spending tool needs.

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?

Front-loaded with the core operation before branching into action semantics, pricing, return value, and the confirmation protocol. It is dense rather than padded, though the long semicolon-chained sentences and the inline Ukrainian label add slight parsing cost without much payoff.

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 stating the return value (new order_id) and the polling follow-up. Combined with the credit cost, the action-dependent quality defaults, and the full confirmation handshake, an agent has everything needed to call this correctly and know what happens next.

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 description coverage is only 14%, so the description must carry the meaning, and it does for most parameters: action semantics and default, style as slug or omitted-for-random, quality defaulting to draft, format restricting to one of the variant's formats, and variant as a numbered position. The idempotency_key parameter is never mentioned, leaving one of seven parameters undocumented in both schema and description.

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?

"Rework one variant of an order into a NEW order" is a specific verb-plus-resource statement, and the description immediately splits it into the two distinct operations (final vs restyle) with what each produces. An agent can tell this apart from creative_order and creative_get 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?

Guidance on choosing the action is explicit: final is the default and means re-render at final quality, restyle means same texts in a different style, with the style slug omitted for a random different one. It also explains how format and quality narrow the operation. It lacks an explicit "use creative_order instead when..." exclusion, which keeps it from a 5.

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