get_task

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

No annotations are provided, so the description carries the full burden. It says it fetches 'current status and latest result payload', which is a mild disclosure of a polling read, but it doesn't disclose the status vocabulary, whether the payload is null or partial while pending, whether the result is preserved after completion, or rate limits for polling. For a polling endpoint with zero annotation coverage this is thin.

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?

One sentence, front-loaded with the verb and resource. No filler or redundant restatement of the name.

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?

There is no output schema, so the description should say more about the return shape than 'status and latest result payload' – e.g., whether status is a string or enum and how the result payload varies per action. Two required parameters and zero annotations also mean the description should explain the polling contract. Adequate but with clear gaps.

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 schema already documents both task_id and the action enum with the note that action identifies the asynchronous endpoint. The description mentions 'kling task' but doesn't add format, mutability, or constraints beyond the schema. Baseline 3 is correct when the schema does all the work.

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 (fetch the status and result payload for a kling task). Clear and distinguishable from siblings, which are all login, video-generation endpoints, or pricing. An agent can tell this is the monitoring/retrieval counterpart to the generation siblings.

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?

No when-to-use guidance. It doesn't say to call this after starting any of the six generation endpoints, nor when to stop polling (e.g., terminal status), nor whether the task must exist. Sibling tools like text_to_video return task ids implicitly, but the description never makes the create-then-get_task loop explicit.

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