Remove Background

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

With no annotations, the description carries the full burden, and it does add real value: it discloses the output artifact (transparent PNG), the preview-on-white rendering quirk, and the returned URL and id. However, it says nothing about latency or model-loading behavior, which matters given the unload_models sibling, nor about input limits or failure modes.

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?

Two tightly-written sentences: the operation and model come first, the return contract second. Every clause carries information and there is 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?

No output schema exists, but the description compensates by naming the return type, preview rendering, URL and id. For a one-parameter read-like transform tool this is nearly sufficient; only execution cost/model-loading context is missing.

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?

There is a single required parameter and schema description coverage is 100%, so the schema already explains that 'image' accepts a server image id or an http(s) URL. The description adds nothing parameter-specific beyond implying a single main subject, so baseline 3 applies.

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 ('cut out') and resource ('main subject') with a concrete effect ('make the background transparent'). It also names the underlying model (BiRefNet), and no sibling (edit_image, upscale_image, generate_image) performs background removal, so the agent can select it unambiguously.

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?

Usage is only implied by the operation name and the phrase 'main subject' – the agent can infer it takes an existing image and removes the background. There is no explicit statement of when to prefer this over edit_image, nor any exclusions or prerequisites (e.g. images with multiple subjects).

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