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

The description adds meaningful behavioral detail beyond the generic false-valued annotations: the operation is asynchronous and returns a job reference rather than a direct file. It stops short of explaining job polling or completion semantics, but it does disclose the most surprising 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?

Two brief sentences with no filler. The first states the action and scope; the second preempts the common expectation of a direct file download. The key constraint is front-loaded.

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?

The description conveys the core invocation contract and the non-file return type, but with no output schema and sparse annotations it leaves an agent unsure how to use the job reference or track export completion. It is adequate for starting the operation but thin for the full workflow.

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?

The schema already documents both optional parameters with defaults, and coverage is 100%, so the description does not need to restate them. The description also adds no extra context about since/until formatting or their effect on the export, so it sits at the schema-covered baseline.

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 clearly states the action ('kick off'), the resource ('async CSV export'), the data scope ('creator's performance data'), and a distinguishing return characteristic ('job reference, not the file'). This separates it from synchronous performance/viewing 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?

The async CSV purpose is understandable, but no alternatives are named and no explicit conditions or exclusions are given beyond 'not the file.' When to use it versus a synchronous analytics/report tool is implied rather than stated.

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