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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses that this is a paid, credit-consuming, non-idempotent generation call, quantifies typical cost per model and duration, and explains the asynchronous job flow: it blocks up to ~50 s then returns a task_id plus email for kling_get_task. That async/next-step disclosure is exactly the kind of behavior an agent cannot get from the annotations or schema.

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 purpose is front-loaded in the first clause, which is good, but the rest is a single dense semicolon-chained paragraph of model specs and pricing that is hard to scan and partly restates schema descriptions. A per-model table or bullet list would earn the same information in less cognitive load; several clauses could be trimmed without loss.

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 22-parameter, zero-required, no-output-schema tool, the description covers the essentials an agent needs: default model, cost profile, duration/mode constraints per model, mutual exclusion between prompt and shot_N params, and what the call returns plus the follow-up tool. Nothing critical is left to guesswork.

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 baseline is 3, but the description adds cross-parameter constraints the schema cannot express: duration limits vary by model, negative_prompt/cfg_scale are older-model only, enable_audio=false is cheaper on kling-v3-0 and that native audio on kling-v2-6 requires pro mode, and 21:9 is kling-v4-0 only. It adds useful meaning, though some of it (audio, negative_prompt) is duplicated from the per-parameter schema text.

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?

The opening clause states a specific verb and resource ('Generate a video from a prompt') and immediately scopes the variants (custom multi-shot via shot_N params on kling-v3-0/v4-0). The name and description together make it obvious this is text-driven generation rather than image-driven. However, it never explicitly contrasts itself with siblings like kling_image_to_video or kling_extend_video, so the differentiation is inferred from the tool name rather than stated.

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 substantial selection guidance: per-model duration ranges, allowed modes, audio defaults, which models accept negative_prompt/cfg_scale, which run pro-only, and relative credit costs so the agent can pick cheaply versus at quality. What's missing is routing guidance against siblings ('if you already have a start image, use kling_image_to_video'), and no explicit statement of when not to use this tool.

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