gflow_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 well: it discloses output count (1-4), the return format (local file paths), model behaviors, and a specific failure mode (entity/image4 not ported on flow.google.com, fails before submit and retrying won't clear it). It omits auth/credit or rate-limit behavior, keeping it below a 5.

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-loads the purpose and keeps the whole definition to a compact paragraph, with enumerations (models, aspects) efficiently inline. A couple of clauses are dense run-ons, but nothing is wasted.

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 16-param tool with no annotations, and where an output schema already exists, the description equips an agent with the essential calling context: options, reference strategy, and the platform caveat. The undocumented secondary parameters leave a residual gap.

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 coverage is 0% across 16 params, so the description must compensate. It adds real value for the key params (model names with quality/speed tradeoffs, valid aspect values, prompt @mention syntax, reference_images vs entity references), but twelve params (seed, wait, count, tools, output, profile, project, ui_mode, instructions, project_name, etc.) get no explanation at all.

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 using Google Flow's Imagen model) and scope (1-4 images from a text prompt). It is immediately distinguishable from the sibling gflow_generate_video.

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 concrete conditional guidance: use @Name for saved named assets vs reference_images for one-off images, and use an existing project with local reference files on flow.google.com accounts where UUID/entity references and image4 fail before submit. It stops short of explicitly contrasting with sibling alternatives, but the routing rules for references and platform are genuinely actionable.

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