flow_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 delivers: it discloses credit consumption, the exact default sequence (fill prompt, pick model/ratio, screenshot, return 'ready_for_confirmation', no Generate click), the confirmation sequence, and that images are then downloaded. This is rich, non-obvious behavioral detail an agent cannot 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?

The credit warning is front-loaded, followed by the two operating modes in sequence, which matches the decision an agent must make. It is dense but nearly every clause earns its place; minor redundancy exists between the description and the auto_confirm schema text.

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 complex 8-parameter mutation tool with no annotations and no output schema, the description covers credit cost, mode gating, model restriction, and the return signal ('ready_for_confirmation'). It could say more about what the download yields or how reference_images influence output, but the essentials for correct invocation are present.

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 100%, so the baseline is 3, but the description adds value by clarifying the model constraint ('NAN/BANANA modèles image seulement') and the credit cost tied specifically to auto_confirm. It reinforces rather than merely repeats schema semantics, though most parameter detail still lives in 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?

The description names a specific verb+resource (generate image) and explicitly scopes it to image models, warning that the UI must be in IMAGE mode 'pas Vidéo'. This distinguishes it from the sibling flow_generate_video without the agent needing to open either schema.

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 clearly specifies when each mode applies: auto_confirm=false prepares and returns 'ready_for_confirmation' without consuming credits, while auto_confirm=true verifies mode/model then clicks Generate and consumes credits. The when-to-use guidance is strong, though it never explicitly names a sibling tool to use for the alternative (video) case.

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