remove_background

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

The description discloses the method (flood fill from four corners), the output format (RGBA PNG), and the fallback mechanism. However, since no annotations are provided, the description carries the full burden. It does not mention whether the operation is destructive, performance characteristics, or required permissions. The behavioral disclosure is adequate but not thorough.

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 exceptionally concise: one opening sentence that encapsulates the core functionality and a structured Args block. Every word contributes value, no filler. The structure front-loads the purpose and then details parameters logically.

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 the tool's moderate complexity (background removal with potential model fallback) and the absence of an output schema, the description covers the key aspects: input, output, method, and parameter roles. It lacks details on edge cases (e.g., what happens with non-solid backgrounds), but these are not necessary for typical usage. Completeness is high for the information provided.

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?

Despite 0% schema description coverage, the description's Args section adds meaningful semantics to all four parameters: src and dst are paths, tolerance is the color difference threshold (0-255), feather is alpha decay (0=sharp, 1=fully transparent). This compensates significantly for the schema's lack of descriptions, providing clear meaning beyond names and types.

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 states the tool's purpose: removing solid or off-white backgrounds via four-corner flood fill with a fallback to a background removal model. It uses a specific verb ('transparentize' implied) and resource ('background'), and is clearly distinct from sibling tools like pixelize or autocrop.

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?

No explicit guidance is provided on when to use this tool versus alternatives. The description mentions a fallback to a background removal model, but does not specify when the flood fill fails or how to decide between this tool and other background removal methods. There are no 'when not to use' statements.

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