Build Dataset

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

The description adds significant behavioral detail beyond the annotations: it reveals that the build is asynchronous ('Returns a job_id immediately — poll with job.status until status='completed'), explains the response includes a dataset_id, and describes the required workflow. Annotations only indicate non-readonly and non-destructive, but the description enriches this with async nature and polling instructions.

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 description is concise (around 10 lines) and well-structured: a one-sentence summary, followed by behavioral notes, then an Args section. Every sentence provides essential information. The structure is front-loaded with the core purpose and step number, making it easy to scan.

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 covers all necessary aspects for a tool in a workflow: prerequisites (completed execution), side effects (async build, dataset created), return value (job_id), and next steps (poll and then export). Given the presence of an output schema, the description does not need to detail return format. It provides a complete context for correct usage.

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 0% schema description coverage, the description fully compensates by providing detailed semantics for all parameters: execution_id is from a completed data_process job, name is auto-generated from filename if omitted, description is optional. This adds crucial context absent from the schema, making parameter usage clear.

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 tool's purpose: 'Package extracted records into a dataset for export (Step 4)'. It specifies the action (build), the resource (dataset), and its role in a multi-step workflow. It distinguishes itself from sibling tools like dataset.export and job.status by explaining that this step is required before export and that the returned job_id must be polled.

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 provides explicit when-to-use guidance: 'Triggers an async dataset build from a completed execution.' It states the prerequisite (completed execution) and the subsequent step ('This step is required before calling dataset.export'). It also tells the user to poll job.status until complete, offering a clear usage pattern. No alternative tools needed for this specific step.

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