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

Annotations only declare the generic write/async profile, but the description adds highly specific behavior: model-version support limits, the exact error code on refusal, an approximate cost (~20 credits), the extension length, and the same-account requirement. It also frames the result as an async job, which is exactly the operational context an agent needs and cannot get from the annotations.

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?

Extremely dense and front-loaded: capability, version limits, cost, job model, and endpoint each get one clause with zero filler. The most decision-relevant facts (what it does, what it rejects) come first.

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 job with no output schema, the description covers cost, eligibility, failure mode, account scoping, and the returned-job nature, referencing kling_text_to_video as the behavioral template. An agent has everything needed to decide whether to call it and what to expect.

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 description coverage is 100%, so the schema already documents all six parameters. The description only reinforces the same-account constraint for 'email' and the duration semantics, adding little beyond the structured fields. Baseline 3 applies.

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 (continue/extend) and resource (a finished Kling video task) with the exact scope (~5 s continuation). It names the sibling kling_text_to_video as a structural analog and the endpoint, letting an agent place it precisely among the many kling_* generation 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?

Gives clear preconditions: must be a finished task, same account, and only kling-v1-6 videos qualify. It also names the failure case (kling-v2-6 refused with TASK.InvalidTaskType), which effectively tells the agent when not to use it. It stops short of an explicit 'use X instead for newer models' routing statement.

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