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

Annotations only declare readOnly=false, openWorld=true, destructive=false. The description adds the operationally critical traits annotations cannot express: it is SLOW (~30-40s), it returns the image inline, and it prescribes a pre-call UX step to avoid the wait looking like a hang.

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 capability and differentiators, then the return behavior, then the latency warning and the action to take. Every clause carries information; no filler.

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, but the description compensates by stating the image is returned inline and how long it takes. Combined with 100% schema coverage on both parameters, an agent has everything needed to call and wait 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 description coverage is 100% with 2 parameters, and the enum of aspect ratios is fully documented in the schema. The description adds no format, syntax, or constraint detail beyond the schema, so the baseline of 3 applies.

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+resource ('Generate an image') and pins down the exact backend (Google's Nano Banana / Gemini 3 Pro Image), which distinguishes it from the sibling generators generate_image_flux and generate_image_seedream. It also names the domains where it wins (photorealism, legible text, complex compositional prompts), so an agent can choose without opening schemas.

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 explicit selection criteria ('best for photorealism, legible text in the image, and following complex/compositional prompts') that route the agent among the image-generation siblings. It also adds a concrete invocation-time instruction: tell the user it is generating ~30 seconds BEFORE calling, so the wait is expected.

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