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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely new behavior: the model/quality ('Nano Banana 2 at 1K'), that it consumes credits, and the synchronous-vs-pending return pattern. It stops short of saying what happens on failure or how many credits are consumed.

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?

Three tight sentences, front-loaded with the primary capability, then cost, then return semantics. No filler or redundancy.

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?

With no output schema, the description correctly explains the return shape (direct image or pending + get_image) and discloses credit cost, which is what an agent needs to plan a call. Error handling and credit quantities are the remaining gaps.

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 100%, so all three parameters are already documented with constraints and enum values. The description implies the prompt/image_urls relationship but adds no syntax, ordering, or format guidance beyond the schema, which is the expected baseline here.

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?

Names specific verbs (generate, edit) and the resource (image), and enumerates concrete edit types (background, outfit, style, lighting, combine). An agent can distinguish this from create_video or animate_photo without opening the 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?

Gives a clear usage fork ('omit image_urls to generate from text only') and an explicit follow-up path ('if status is pending, call get_image later'). It does not route against near-siblings like restore_photo or animate_photo, so selection between those remains inferred.

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