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

Annotations declare the write/open-world profile, and the description adds genuinely new context beyond them: the cost model ("1 credit per image"), the result shape ("Finished images come back as images you can see"), and the underlying endpoint. It does not clarify whether the call blocks or returns a task_id to poll with kling_get_task, which is the main remaining 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?

The core purpose is front-loaded, but the body is a dense run-on of parentheticals that mixes version notes, credit cost, and an endpoint path. "POST /images/kolors" is internal plumbing that adds little for an agent and could be dropped to tighten it.

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 a 21-parameter generation tool with no output schema, the description covers the essentials an agent needs: cost, output form, version selection, reference-image limits, and conditional requirements. Remaining detail (per-parameter ranges, enums) is fully carried by the schema at 100% coverage.

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 already 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema states only in scattered per-field text: that aspect "auto" requires a reference on kling-v3-0, that reference modes require imageReference, and that imageCount defaults differ by version. That version-conditional coupling is real added meaning beyond the schema.

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 ("Kolors images from a prompt") and enumerates the two operating modes (kling-v3-0 with up to 10 reference images vs. older versions with reference subject/face/restyle). An agent can tell this is the prompt-to-image generation tool, though it never explicitly distinguishes itself from the similarly named kling_kolors_elements_image sibling.

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 useful intra-tool routing (default kling-v3-0 with reference images; older versions when you want subject/face/restyle), which implies when each mode applies. However it offers no guidance on when to pick this tool over the many sibling image tools (kling_omni_image, kling_enhance_image, kling_kolors_elements_image), so alternative selection 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.