Describe Image (Nano Banana Pro)

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly states the output is text and that no image is generated, and mentions the default model. The timeout recommendation is also included. However, it does not mention potential side effects, rate limits, cost implications, or any details about how the images are processed besides the model hint. This is adequate but not rich.

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?

The description is compact — two sentences plus a timeout recommendation. The core purpose is front-loaded: 'Analyze and describe...' The rest is supplementary. Every part adds value: the output type, the no-generation assurance, and the default model. No fluff 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?

Given the tool's moderate complexity (4 params, nested images object, output schema present), the description covers the essential purpose, output, and default model. The schema handles parameter details, and the output schema clarifies return values. The timeout hint is a plus. However, it doesn't differentiate from the similar analyze_image sibling, which might be a slight gap. Overall, it's sufficiently complete for a description-focused tool.

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% — every parameter (model, images, prompt, global_media_resolution) is well-described in the schema, including sub-fields like filePath, mimeType, and mediaResolution. The description itself adds minimal parameter info beyond the schema, but since the schema covers everything, the baseline of 3 applies. The description does note the default model, which matches the schema's instructions.

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 description clearly states the tool's action: 'Analyze and describe one or more images' using Gemini models, and specifies the output: 'Returns a text description'. It also explicitly notes that no image is generated, which differentiates it from generation tools like generate_image. The verb+resource+output is specific and unambiguous.

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?

The description provides clear context on what the tool does (describes images, returns text) and implicitly indicates it's for description rather than generation. However, it does not explicitly mention when to use this over alternatives like analyze_image or when not to use it. The 'no image is generated' hint suggests it's not for image generation, but no explicit alternatives or exclusions are given.

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