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

Annotations only declare readOnlyHint=false, so the description must carry the rest — and it does: cost ($0.04), workspace-local storage with no provider links, refund semantics on output-flagged and undelivered results, safety-check outages that charge nothing, and idempotency via request_ref. This is well beyond what the annotation gives.

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?

Price and core behavior are correctly front-loaded, but the mid-section is a long run-on catalog of refusal codes that is dense and hard to scan. The information mostly earns its place, yet the formatting as one prose block costs readability.

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, the description fully specifies the return shape ({images:[{url, asset_key, download_url?, width, height}], price, next}), the preview block, and the failure taxonomy. An agent can call, interpret, and recover from this tool without further documentation.

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%, with rich per-parameter text for image_url, request_ref, preview_format and image_asset_key. The description adds little parameter-level meaning beyond the schema, except that an empty prompt will fail with VALIDATION_ERROR ('name the look'), so the 3 baseline is appropriate.

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+effect: 'Apply a style to a photo while preserving the content', and even names the engine and strength (FLUX img2img, 0.55). It does not differentiate from near siblings like image.variation or image.adjust, which is the only thing 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?

Chaining guidance is explicit ('pass images[0].asset_key as image_asset_key to the next image.* tool, or open download_url'), and each refusal code carries a remediation step. However, there is no guidance on when to choose this over image.variation or image.adjust, so tool-selection remains implied.

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