generate_image

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

With no annotations, the description carries the full burden. It does disclose the key async behavior — returns a job rather than the image, poll to retrieve — which is real value. It omits auth requirements, cost/credit implications, latency expectations, and failure modes for a remote generation call.

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 short sentences, front-loaded with purpose and followed by the async contract and polling route. The raw endpoint path is mildly redundant for an agent, but nothing is padded.

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?

For an asynchronous job-creating tool with no output schema, the description correctly conveys that the return value is a job handle and names the polling tool, which is the critical missing piece. Parameter-level and auth detail remain thin, but the call pattern is complete enough to invoke and follow up.

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 57%, below the threshold where the schema can be assumed to do the work, and the description adds no parameter meaning at all. Notably the model and resolution enums carry no descriptions, and the distinction between file_urls, ref_history, and style is left entirely to the schema.

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 (Generate) and resource (image) and pins down the model family ('snapgen nano-banana models'), which implicitly separates it from siblings generate_gpt_image and generate_grok_image. It does not explicitly name those siblings, so it stops short of a 5.

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 gives the follow-up path clearly ('poll with get_generation'), which is genuinely useful routing. However it never says when to choose this tool over generate_gpt_image or generate_grok_image, so the core selection decision is left to inference.

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