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

With no annotations, the description carries the full burden and does so well: it discloses per-model cost (~10 coins, 1 coin, 18-24), the default resolution, the 7-input reference limit, and that the tool is asynchronous (returns job_id; poll check_job until done). These are the behavioral traits an agent cannot infer from the schema alone.

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?

Despite its length, every sentence is actionable guidance with no filler, and the most important constraint (default model and default resolution) is front-loaded. Sentence-level imperative style keeps it scannable.

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?

No output schema exists, and the description fills that hole by stating the tool returns a job_id and must be polled via check_job. Combined with cost, defaults, limits, and refusal-to-guess guidance on aspect ratio, an agent has everything needed to invoke this correctly.

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 only 50%, so the description usefully compensates by explaining model trade-offs, the resolution default, the ask-first policy for aspect_ratio, and the semantics of reference_image_urls (multi-character, up to 7 total, order matters). It leaves four enum models (google_nano_banana, google_nano_banana_edit, gpt4o_image, gpt_image_2) completely unmentioned, which is a real gap given the 7-value enum.

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?

The first sentence states a specific verb+resource ('Generate an image') and the rest makes the operation unmistakable. It also names the related sibling 'check_job' as the polling counterpart, so an agent can distinguish this from generate_video and check_job 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?

Explicit routing rules for every meaningful choice: default model nano_banana_2, z_image only for cheapest, nano_banana_pro only for face preservation/max quality, and never 2K/4K unless asked. It also states the condition under which the agent should stop and ask about aspect ratio, which is exactly the when/when-not guidance this dimension rewards.

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