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

Annotations only declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds far more: the source is left unchanged, soft shadows and reflections are removed, the result carries sourceAssetId, colors, transparentShare, source category and a source-naming description, and rendering MCP clients also receive the image. It also discloses billing treatment (no credits) and a hard quota of 10,000 per organization per calendar month.

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?

The core behavior is front-loaded in the first clause, followed by progressively finer details (result metadata, edge behavior, quota, skill prerequisite). It is dense and semicolon-heavy, but each clause carries distinct operational information rather than restating the name or title.

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 and minimal annotations, the description still covers what is produced (metadata fields and the rendered image), what is preserved (source asset), what is dropped (shadows, reflections), quota, and cost. An agent has everything needed to call it correctly and anticipate the result.

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 50%: `trim` is already documented in the schema and the description largely restates it. However, `assetId` has no schema description, and the description compensates by explaining it is the source asset, that it must be a ready image in one of the listed formats belonging to the same website, and that the result is derived from it rather than modifying it.

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 concrete verb and resource: creates a new PNG asset with the main subject isolated on a transparent background. It names the accepted source formats and clarifies that the source is unchanged, which separates it from websiteAssets_update and websiteAssets_importFromUrl without the agent needing to inspect those schemas.

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 prerequisites are explicit (source must be a ready PNG, JPEG, WebP, GIF, or AVIF image of the same website) and it directs the agent to run skills_read on the assets-and-media skill first. It stops short of naming alternatives or exclusions, so it gives clear context rather than full when/when-not routing.

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