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

Annotations already declare the write/openWorld/non-idempotent profile, and the description adds genuinely new operational context: cost (~1 credit per image), asynchronous job semantics, and the HTTP endpoint. It still doesn't say how the job's result is retrieved (e.g., via kling_get_task), which is the one behavioral gap.

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?

A single dense sentence plus two short fragments: the composition model comes first, then cost and job semantics. No filler and nothing important buried.

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?

For an async generation tool with no output schema, it covers inputs, cost, and job nature adequately. It stops short of naming the polling/retrieval path for the resulting task, which is the main thing an agent still has to infer from sibling tools.

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 real meaning beyond the schema: the effective minimum of two images (the schema lists required=[], so nothing enforces it) and the mapping of subjectImage1..4 to 'subjects' versus the optional scene/style roles in the composition.

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: multi-image composition combining up to 4 subjects with optional scene and style images, guided by a prompt. The Kolors 2.1 / 'elements' framing and the 'up to 4 subjects' scope separate it from the single-image kling_kolors_image, though it never names that sibling explicitly to make the boundary airtight.

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?

It gives one hard usage rule ('give at least two images') and notes the job pattern via 'like kling_omni_image', which is a useful pointer. However it never states when to prefer this over kling_kolors_image or kling_omni_image, so the selection decision is left implied rather than stated.

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