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

With no annotations present, the description carries the full burden. It explicitly warns that the call spends paid quota and starts real work on the user's balance, requires auth, and is asynchronous. This is strong transparency, though it stops short of describing failure modes or cancellation behavior.

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 cost warning is front-loaded, then auth requirements, then the workflow. Four sentences with zero filler. The async flow is clearly separated from the initial call.

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 state-changing, paid, asynchronous operation, the description covers consent, prerequisites, return value, and follow-up calls. It doesn't detail error responses, but that's minor given the sibling tools and schema guidance.

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?

Input schema already documents all three parameters well, including the Russian-register warning and the role of list_task_kinds. The description adds no parameter meaning beyond the schema; baseline 3 is appropriate.

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 description states a specific action ('Start a data collection run'), the key output ('return its id'), and makes the asynchronous lifecycle explicit. This clearly differentiates create_task from sibling tools like get_task and get_task_result.

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?

The description gives clear usage context: ask the user before spending quota, requires an active subscription and API key, and explains the polling workflow. It does not explicitly contrast with sibling tools, but the workflow reference makes the relationship clear.

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