Generate or edit image (Nano Banana)

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

No annotations are provided, so the description carries the full disclosure burden. It does useful work: it explains the mode switch on inputImages and that it returns local paths plus a preview. But it never says whether generation is synchronous or returns an operation id to poll (relevant given the flow_check_operation sibling, which implies async work exists), nor anything about cost, latency, or failure modes. A meaningful gap for a generation call with zero annotation coverage.

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?

Four sentences, front-loaded with capability, then mode logic, then workflow handoff, then return shape. Nearly every sentence earns its place; the only soft spot is the 'as in Flow's image tools' clause, which adds little for an agent.

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 compensates by naming the return values (local paths and a preview). It is nearly complete for a creative-generation tool; the missing piece is whether the call blocks until the image is ready or requires polling via flow_check_operation.

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 71%, so the schema documents most parameters, including aspectRatio guidance for video keyframes. The description adds genuine semantics the schema does not: the presence or absence of inputImages is what selects text-to-image versus edit/restyle/combine, which reframes inputImages as a mode flag rather than a plain array. It does not elaborate on model overrides or numberOfImages.

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 specific verb and resource (create/edit images) plus the underlying models (Nano Banana / Imagen), then splits the tool into two clearly named modes: text-to-image without inputImages, and edit/restyle/combine with them. This is enough to distinguish it from flow_generate_video and the other siblings without opening a 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 concrete usage context: build characters, props and keyframes, then hand the returned asset ids to flow_generate_video as startImage/endImage/referenceImages. That is an explicit workflow handoff. It stops short of stating when NOT to use it (e.g. when to prefer flow_generate_video or flow_extend_video), so it is clear context rather than full routing guidance.

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