Remove Background

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

With no annotations, the description carries the full burden. It does disclose the mechanism (AI subject isolation) and the quality dependency, which is real behavioral context. However, it omits that the tool produces a new image file on disk, whether existing files can be overwritten, and any cost or rate considerations — material for an unannotated write-style tool.

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?

Three short sentences, front-loaded with the action, then mechanism, then the one caveat that affects success. 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?

An output schema exists and all three params are fully documented, so return values need not be explained. The remaining gap is the absence of any note about where the resulting file lands or whether the operation is billed, which an agent would want before invoking.

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 description coverage is 100%, so the schema already fully documents image_path, output_format, and output_filename. The description adds nothing about parameter behavior (e.g., that png preserves transparency for the cutout), so the 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+resource: 'Remove the background from an image,' which an agent can immediately distinguish from siblings like edit_image, transform_image, and upscale_image. It doesn't explicitly name the neighboring tools it is not, but the operation is unambiguous on its own.

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?

'Best results with clear subjects against distinct backgrounds' gives a quality precondition, which is useful, but the description never says when to choose this over edit_image/advanced_edit or what happens if the subject is unclear. Usage is implied rather than routed.

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