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

Annotations already declare the safety profile (write, non-idempotent, open-world), and the description adds real behavioral context beyond them: video length tracks the speech, cost is 4 credits/second at std and 8 at pro, and the call produces an asynchronous job like kling_text_to_video.

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 paragraph with no filler: purpose, input matrix, length/cost, and async nature all front-loaded. Every clause carries information an agent needs.

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 10-parameter, no-required, combinatorial tool with no output schema, it covers the input matrix, pricing, and job semantics well. It stops short of stating how to retrieve the resulting video (polling via a task tool), which the 'A job' phrasing only implies.

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?

With 100% schema coverage the baseline is 3, but the description adds the crucial combinatorial logic across the 0-required-parameter set: avatarId vs imageUrl are alternatives, audioUrl vs text+speakerId are alternatives, and an avatar carries its own default voice. This clarifies valid input pairings the per-parameter schema text only states individually.

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?

Opens with a concrete verb+resource ('A talking-head video') and immediately enumerates the two avatar sources and two speech sources. It names kling_list_avatars as the source of avatarId and references kling_text_to_video, letting an agent separate this from sibling video tools.

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?

Explains which input combinations apply (avatar or portrait; audio or text+speakerId) and that an avatar supplies its own voice. It routes to kling_list_avatars for avatarId, but never contrasts the tool with the closely-related kling_lipsync sibling, so guidance is clear context without explicit exclusions.

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