Editar imagem / gerar com referência

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

With no annotations, the description carries full burden. It discloses that multiple images are accepted, an optional mask is used (with OpenAI model restriction), and the result is saved to disk with paths returned. However, it does not detail write behavior (overwriting), error handling, or prerequisites beyond model-specific mask support.

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 description is three sentences, front-loading the primary purpose with a clear directive. No redundant phrases; every sentence adds essential information (use cases, input details, output behavior).

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?

Given 7 parameters, no annotations, and no output schema, the description adequately covers the tool's main use, input expectations, and outcome (saves to disk and returns paths). It lacks output format specifics and prerequisites but is sufficient for an image editing tool.

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%, baseline 3. The description adds value by clarifying the mask parameter is only for OpenAI models (not in schema) and reinforces the purpose of each parameter through contextual usage examples. This exceeds the baseline.

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 clearly lists the specific actions: edit existing image, generate new based on reference, combine elements, transfer style, or create variations. It explicitly states the tool is for use with starting images, distinguishing it from sibling 'generate_image' which likely generates without references.

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?

The description begins with 'Use always when there are starting images' and lists concrete use cases, providing clear context. However, it lacks explicit 'when not to use' statements or direct references to sibling tools like 'generate_image' for no-reference generation.

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