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

Annotations already cover safety (non-read-only, non-idempotent, non-destructive, open-world). The description adds the crucial behavioral fact that this is a paid operation with two billing paths and a price quote before spend, which annotations do not convey. It omits whether the call is async and how the result is retrieved.

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 tight sentences; the capability comes first followed by the billing constraint. No filler or repeated structured data.

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 paid, non-idempotent media tool with zero required parameters and no output schema, the description should clarify that image or image_url must be supplied and how the processed image comes back. It covers cost but not the call contract.

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 each parameter is already documented, including the image vs image_url split and the max_usd/max_credits confirmation rules. The description only contributes the notion that a price is quoted first, which loosely ties to the max_* parameters; 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 and outcome: cut out the subject and make the background transparent. That distinguishes it implicitly from erase_object (removes a thing) and split_layers (separates layers), but no sibling is named explicitly.

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 gives billing context (credits via OAuth, USD via API key, with a quoted price) but never says when to pick this over erase_object, remove_shadow, or split_layers. Usage is only implied by the stated outcome.

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