Masked edit: replace, remove, change material (Magic Wand AI)

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

Annotations already declare the non-read-only, non-destructive, open-world profile, so the description only needs to add beyond that. It does: a per-call cost of 1 credit, the constraint that the mask must be the same size as the input, and the white-marks-the-target convention. It omits permission/auth requirements and whether calls are async.

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?

Front-loaded with the core action, then mode selection, then mask mechanics, then cost — a sensible priority order in four tight sentences. The mask color/size explanation partially duplicates the schema's mask_image description, which is the only minor redundancy.

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 10-parameter generative tool with no output schema and no annotation coverage of output handling, the description leaves out how results are retrieved (no mention of luw_get_result or whether the tool returns the image directly) and what happens if prompt, remove, and material_image are combined. Mask sourcing and credit cost are covered, so it is adequate but not 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 coverage is 100%, so the baseline is 3, but the description adds genuine semantic value by explaining the interaction between modes: remove=true erases rather than generates, and material_image applies a texture instead of a prompt-described object. That tells the agent how to choose among parameters, not just what they are.

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 names a specific verb and resource ('change only a masked area of an image') and enumerates the three edit modes (prompt add/replace, remove, material_image), which clearly separates it from full-image edit tools. It stops short of naming the sibling it displaces (e.g. luw_edit_image or luw_remove_furniture), so sibling differentiation is implied rather than explicit.

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?

It gives concrete selection rules: use a prompt to add/replace, remove=true to erase, material_image to re-surface, with a domain example ('new flooring or wall tiles'). It also routes the agent to luw_segment for obtaining masks. What's missing is an explicit when-not-to-use, i.e. that whole-image edits belong to luw_edit_image.

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