generate_image

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

With no annotations, the description carries the full burden and does disclose two valuable traits: images cost no credits and exact-size requests are achieved by native-ratio generation plus cropping. It omits important behavior for a write-to-disk tool: authentication requirements, whether existing files are overwritten, generation latency, failure modes, and what the tool returns.

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 what the tool does and what it produces, followed by the most decision-relevant caveat (the crop behavior). No filler or repetition of schema content.

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 a twelve-parameter tool with no output schema and no annotations, the description is thin at the edges: it does not say what is returned (file paths, a confirmation, a count), how out_dir/FLOW_OUTPUT_DIR behaves when missing, or how reference_images interact with prompt length limits. The core workflow is explained adequately, but an agent still has open questions before calling it.

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 already 100%, so the baseline is 3, but the description adds genuine cross-parameter meaning the schema does not: the interaction between size and aspect (closest native ratio is chosen automatically, then cropped). That is real interpretive value beyond the per-field descriptions, though it covers only two of twelve parameters.

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 ("Generate one or more images with Google Flow") plus the side effect ("save them to disk"), which clearly separates it from siblings like generate_video, upscale_image, and download_image. It stops short of naming any sibling explicitly, so differentiation is inferred rather than stated.

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?

It gives useful conditional guidance for the size parameter ("ask for an exact pixel size... generates at the closest native aspect ratio and crops") and a cost note. However, it never says when to prefer this over generate_batch, upscale_image, or download_image, and no prerequisites 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.