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

Goes far beyond the single readOnlyHint=false annotation: declares the $0.02 price, states results are stored in this workspace rather than provider links, explains download_url_unavailable, documents the refund-and-retry semantics of SIMPLER_EDIT_RESULT_UNDELIVERED, and enumerates refusal codes with remedies. This is exactly the behavioral context the annotation does not carry.

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?

Cost and purpose are front-loaded, then returns, then refusals, then next action — a sensible order. The error-code clauses and parentheticals make it dense, but virtually every sentence carries operational information an agent would otherwise have to discover by failing.

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?

With no output schema available, the description compensates fully by specifying the JSON return shape (images array with url/asset_key/download_url/width/height, price, next) and the preview block. Combined with error semantics and next-step guidance, an agent has everything needed to call this correctly on the first attempt.

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; the description still adds meaning by tying image_asset_key to workspace scoping (SIMPLER_MEDIA_FOREIGN_KEY) and to the chaining contract ('pass images[0].asset_key as image_asset_key'), and by reinforcing the url-or-asset_key exclusivity at the error level.

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 resource ('Remove the background from a photo, returning the subject on transparency') and even names the underlying model, so the agent knows exactly what output to expect. It does not explicitly distinguish itself from near-siblings such as image.replace_background or image.segment_at, which is the only gap keeping it from a 5.

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 clear input conditions (url or asset_key, error codes for refusals) and a concrete NEXT step for chaining into other image.* tools, which is strong pipeline guidance. However, it never says when to choose this over image.replace_background or image.segment_at, so competitive selection among siblings is left to inference.

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