Remove or replace background

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

Annotations already declare the safety profile (readOnly=false, openWorld=true, idempotent=false, destructive=false), so the description's main added value is the credit cost ("Costs 1 credit") and the transparent-PNG output. It does not disclose the return/retrieval flow or any async behavior, which matters for a generation tool, leaving a meaningful gap despite the useful cost disclosure.

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 core behavior is front-loaded, examples are embedded inline, and the cost note is a single trailing clause. Every sentence carries information about what the tool produces or how to trigger each mode, with no filler.

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 single-required-param generation tool with no output schema, the description covers both modes, output type, and cost. The one missing piece is how results are retrieved (likely async via luw_get_result given the sibling set), which an agent would otherwise have to infer from other tools.

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%, so the baseline would be 3, but the description adds genuine value by illustrating prompt syntax with a concrete scene example ("on a marble kitchen counter, morning light") that shows the expected natural-language style. It does not touch engine or format, but the schema already covers those, so this is above 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?

States a specific verb+resource ("Change Background") and immediately enumerates the two distinct behaviors: cut out the object to a transparent PNG, or generate a new scene when a prompt is given. This clearly separates it from neighbors like luw_remove_furniture (furniture-specific) and luw_edit_image (general edits). An agent can pick this tool without opening 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?

Gives explicit mode-selection guidance: include a prompt to place the object in a generated scene, omit it to just remove the background. It also signals the marketing-shot use case, which helps an agent decide when to reach for it. It stops short of naming a sibling alternative or stating exclusions, so it is clear context without routing.

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