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

Annotations only declare this is a non-readOnly, non-idempotent, non-destructive write. The description goes well beyond them by disclosing concrete runtime behavior: RECIPE_MODEL_UNFIT with a reason, automatic snapping of pinned settings (ratio/resolution/length/format) to the nearest supported value, and clip-shape coercion. It omits cost/credit implications, which would be valuable for a generation tool.

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?

Purpose is front-loaded, but the remaining text is a dense run-on of em-dash and parenthetical clauses that is heavy to parse. Most clauses carry real information (subject preference, model fitness rules), yet the packaging could be split into cleaner sentences or bullets.

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 5-parameter tool with nested objects and an output schema (so return values need not be described), the description covers the essential behavior: recipe inputs, subject binding, model override rules, and failure semantics. It is nearly complete, missing only practical notes like cost or the required recipe_id acquisition path.

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 0%, so the description carries the full burden and largely succeeds: it explains creative_prompt (a brief on reprompt recipes), choices (one value per get_recipe choice), model_id (default vs. tested models and fitness failure), and the nested inputs shape including media binding and the subject contract. It does not surface schema constraints like maxItems/minItems, but meaning is well conveyed.

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 first sentence states a specific verb, resource, and scope: create ONE image or clip using a guided recipe (arm or reprompt). This cleanly distinguishes it from siblings like generate_image, generate_clip, and start_recipe_run without the agent needing to open any 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 establishes the workflow prerequisite — supply creative_prompt and one value per choice that get_recipe declares — and explains the model-selection path (use allowed_models vs. another model of the same medium). However, it never explicitly states when NOT to use this tool (e.g., vs. plain generate_image), leaving that routing to inference.

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