create_dataset

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

Annotations only indicate non-read-only/non-destructive behavior, so the description adds value by disclosing that the dataset starts in DRAFT state, that files must be uploaded before it becomes READY, and that the name is unique within the account. It also clarifies the omission behavior: RunComfy generates a name. This goes beyond the annotations without contradicting them.

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?

Every sentence earns its place: the one-line purpose, the endpoint mapping, the lifecycle instructions, and the parameter documentation. It is detailed but not padded, and the most actionable information 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?

For a low-complexity tool with one optional parameter, the description covers creation, initial state, next steps, and naming semantics. The only notable gap is that it does not state what the API returns (e.g., a dataset ID or generated name), which would be useful when name is omitted and the agent needs to reference the dataset afterward. Still, the workflow is clear enough for correct invocation.

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 0%, but the description fully compensates by documenting the only parameter, name: it is human-readable, unique within the account, used as the dataset_name in AI Toolkit config paths, and optional with auto-generation behavior. This is a model example of the description carrying the parameter-semantics burden that the schema lacks.

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 uses a specific verb and resource: 'Create an empty training dataset.' It clearly distinguishes itself from sibling dataset tools by emphasizing 'empty' and 'training dataset', and from lifecycle tools like get_dataset_status and submit_training_job by framing this as the initial creation step.

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 a clear workflow: create the dataset, upload files, poll get_dataset_status until READY, then submit a training job. This effectively tells the agent when to use this tool and what comes next. However, it does not explicitly say when not to use it or contrast it with alternative dataset-creation paths.

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