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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so the safety profile is covered. The description adds real, non-obvious behavior: the resulting recipe is private, reference images are deliberately not carried over (with the rationale), and the empty-brief vs typed-brief replay semantics. It stops short of saying whether repeated saves create duplicate recipes.

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 tight sentences, front-loaded with the core action and then the two behavioral caveats that matter most (brief replacement, dropped reference images). Slightly dense phrasing ('Pressing the result with an empty brief') costs a little clarity but nothing is padding.

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?

An output schema exists so return values need no explanation, and the mutation's downstream effect is well covered. But with zero schema description coverage and no mention of tags/description, an agent cannot fully determine what to pass or how optional metadata affects the saved recipe.

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 it addresses only two of four parameters: name ('you supply the name') and generation_id implicitly. The tags and description parameters are never mentioned in either the schema or the description, leaving half the surface undocumented.

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 ('Turn a finished image or clip into a private recipe') with the key differentiator against siblings clearly implied: the source is an existing generation, not a from-scratch creation like create_recipe. An agent can distinguish this from create_recipe, generate_with_recipe, and remix_recipe from the description alone.

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?

Implies the precondition that a finished generation must exist and that the generation supplies model/settings/prompt, which is genuine context. However, it never names create_recipe as the alternative for building a recipe without a generation, nor states a when-not case, so routing between the recipe-writing siblings is left to inference.

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