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

With no annotations present, the description carries the full burden of behavioral disclosure, and it delivers: it mentions async 202 behavior, polling via getApiJob with wait: 30, the result field being the documented response, 15MB rejection, credits charged only on success, the 50-job concurrent limit, and the 429 PENDING_JOBS_LIMIT. This is exemplary transparency for a complex 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?

Although the description is long, it is dense and front-loaded with the core purpose. Every sentence covers a distinct operational fact: what it does, how to call it, output shape, validation limits, billing, sibling differentiation, async behavior, and quota handling. This is justified detail, not 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?

Given no output schema and no annotations, the description provides all essential operational context: input format, output shape ('a single image result with a url (not an array)'), error conditions, job polling mechanics, idempotency via request_id, cost, and rate limiting. An agent has everything needed to both select and correctly invoke this tool.

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 the baseline is 3, but the description adds meaningful semantic context beyond the schema: request_id can be used to retrieve the result later via GET /assets/images/results, sending the same request_id returns the existing job, and creative_edit may produce output that doesn't match the input pixel-for-pixel. The schema already documents the params well, so a 4 is appropriate rather than 5.

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 opens with a precise verb and resource: 'Remove the background from a single image, returning the subject isolated on a transparent background.' This clearly states the tool's core function and differentiates it from siblings like editImage, createImage, and generateWithStyle by explicitly framing it as the dedicated cutout task.

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 explicit when-to-use guidance: 'Use removeBackground for this dedicated cutout task; editImage can also remove backgrounds via a prompt but is better for broader edits, while createImage and generateWithStyle produce new images rather than process an existing one.' It also specifies the async polling workflow and concurrency limits, leaving little ambiguity about how to invoke it correctly.

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