gflow_generate_image

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

No annotations are provided, so the description carries the full behavioral burden and does so thoroughly: image count range (1-4), @AssetName resolution into referenceEntities/referenceImages, and the flow.google.com failure mode where 'UUID/entity references and image4 are not ported to that composer yet and fail before submit; retrying will not clear it.' This discloses failure-prone behavior an agent could not infer from the schema.

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?

Six dense sentences ordered logically: purpose → options (models/aspects) → reference strategies → platform caveat → return value. Every sentence carries distinct actionable content; the flow.google.com caveat is long but high-value, and the only marginal redundancy is the return-format sentence that the output schema already covers.

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 the core use case the description is notably complete — an agent can choose a model, aspect, count, and reference strategy and knows what fails and what comes back. But for a 16-parameter tool with zero schema coverage and no annotations, leaving seed, wait, tools, output, profile, project, ui_mode, instructions, and project_name undocumented is a meaningful gap in the parameter surface.

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?

With schema description coverage at 0%, the description must compensate and does cover the core generation params meaningfully: prompt, count (1-4), model (three named values), aspect (five named values), and reference_images vs reference_entities semantics. Nine parameters (seed, wait, tools, output, profile, project, ui_mode, instructions, project_name) receive no semantic explanation in either the schema or description, leaving an agent guessing on a genuine majority of the parameter surface.

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?

First sentence states a specific verb and resource: 'Generate an image using Google Flow's Imagen model,' and the interaction with sibling tools is unambiguous since gflow_generate_video is the only overlapping sibling. Model and aspect enumerations plus the 'Returns local file paths' statement further pin down exactly what the tool does.

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?

Provides rich in-tool guidance: model tradeoffs (nano2 fast, nano-pro balanced, image4 highest quality), reference strategy (@Name for saved assets vs reference_images for one-off images), and the flow.google.com caveat requiring existing projects and local reference files on those accounts. It never explicitly names an alternative tool, but the image-vs-video routing is self-evident from the first line.

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