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

Discloses costs credits, always creates a new generation, original untouched, and explains behavior of merge_bias and style_intensity. These add value beyond the annotations (readOnlyHint false, destructiveHint false) by giving specific cost and non-destructive details. No contradiction.

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 dense but well-structured: starts with core purpose, then cost, then mode breakdown. Each sentence carries info; no filler. Slightly long but appropriate given the tool's complexity.

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 12-parameter tool with no output schema, it covers costs, modes, parameter interactions, and reference semantics. It does not explain resolution or aspect_ratio beyond schema, but those are self-explanatory. It's nearly complete for correct invocation.

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 83%, but the description enriches meaning for many parameters: explains action modes, how reference_id works, merge_bias scale, style_intensity scale, and when to use get_detections. This goes well beyond the schema descriptions.

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 states a specific verb ('edits') and resource ('existing image'), and distinguishes from siblings like expand_image or cutout by focusing on AI-driven restyling. However, it does not explicitly name alternatives, so it's not a 5.

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?

Extensive guidance: lists modes, tells when to use get_detections for item names, explains merge_bias and style_intensity, and clarifies that reference_id can be an asset or generation. It clearly tells an agent how to choose the right action and what parameters to set.

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