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

With no annotations, the description carries the behavioral burden and does well: it explains what the background becomes in each case (transparent PNG/WebP, solid hex colour, blurred original scene) and discloses the return contract, a download URL valid for one hour. It omits permissions, cost/rate limits, and what happens if neither image input is supplied.

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?

Four short sentences, each doing distinct work: what it does, what the output is, how to pick the edge modes, and what comes back. The primary purpose is front-loaded before any option detail.

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 7-parameter tool with no annotations and no output schema, the description covers purpose, key modes, and the return value, and the schema fills the remaining parameter detail. The one gap is that it never states the image input requirement (exactly one of `image_url` or `image_base64`), which the agent must read from the schema.

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 baseline is 3, but the description earns above it by explaining the semantics of `background` values as behaviors (transparency, solid fill, scene blur) rather than just restating the pattern, and by characterizing `refine` and `graphic` by use case. `format`, `shadow`, and the two input fields add nothing beyond the schema.

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?

"Cut the subject out of a photo" gives a specific verb and resource that no sibling (compress_image, convert_image, upscale_image) shares. An agent can immediately tell this is the background-removal tool rather than a generic image transform.

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?

The description states clear conditions for the mode options – `refine` for hair/fur edges, `graphic` for logos or text on a surface ("not for photos") – which is real selection guidance. It does not name alternative tools or say when not to use this tool (e.g. when a plain conversion suffices), so it stops short of full when/when-not coverage.

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