continue_editing

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does usefully reveal the stateful behavior of automatically selecting the most recent image, but it does not describe mutation effects, error behavior if no prior image exists, or what the tool returns. For a tool that performs editing, this is a significant gap.

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 two short sentences with no filler. The core action is stated first, and the key automatic behavior is added in the second sentence. Every word earns its place.

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?

The central ambiguity—which image to edit—is resolved clearly. However, the tool has no annotations or output schema, and the description omits failure behavior, return format, and whether the operation modifies session state beyond the previous image. It is adequate for a simple invocation but not fully complete.

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 100%, so all four parameters (prompt, model, quality, referenceImages) are already documented in the input schema. The description adds no parameter-specific semantics, but the schema already handles that burden, so a baseline 3 is appropriate.

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 uses a specific verb-resource pair ('Continue editing the last generated or edited image') and clearly identifies the target as the most recent session image. This automatically distinguishes it from sibling tools like edit_image or generate_image, which would operate on a newly specified image or create a new one.

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 implies the correct use case: after at least one image has been generated or edited, apply further edits to that same image. However, it does not explicitly state when to use this tool versus edit_image, nor does it mention prerequisites such as 'requires an existing image in session' or what happens if no prior image exists.

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