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

Annotations only declare openWorldHint, so the description carries the burden and does it well: it discloses the server-side implementation (Python + Pillow), the actual keying steps, the auto-recovery path and its risk condition, and that the operation uploads and returns a NEW image_uuid plus keying_mode. That is meaningfully more than the structured fields provide.

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?

Purpose is front-loaded in the first clause and the follow-on sentences carry real information about the fallback path. However, the trailing stray token '[#3cd7e7]' is pure noise, and the parenthetical algorithm list ('flood-fill + enclosed-region sweep + tight crop') is more detail than an agent needs to select the tool.

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 correctly compensates by naming the returned values (new image_uuid, keying_mode). It covers implementation, modes, fallback and return shape, but omits failure behavior (e.g., what happens when the source lacks a green screen and force is not set) and says nothing about the non-required workspace/image_url parameters.

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 60% and the description largely restates the background_mode enum semantics ('auto-recovers by re-keying in green-dominance mode', 'safe for art with no bright-green/lime elements') rather than adding new information. The force parameter and the undocumented workspace parameter are never addressed in the description, so the coverage gap is only partly compensated.

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 precise verb+resource: 'Key a solid background out of a generated image to true RGBA transparency ... and upload the result,' with the algorithm family (flood-fill + enclosed-region sweep + tight crop) named. This is unambiguous and clearly distinct from siblings like generate_image or fit_aspect.

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?

Gives clear operational context: it runs server-side, auto-recovers when the generator emitted a tinted green, and notes the safety condition '(safe for art with no bright-green/lime elements)'. It never explicitly states when to use this versus a regenerate/iterate path, nor names an alternative tool, so it stops short of full routing guidance.

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