kaggle_create_dataset

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

Beyond annotations (which indicate a write operation), the description reveals key traits: async behavior (returns 'queued'), polling requirement, default privacy, environment variable for public, and required metadata file. No contradictions with annotations.

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?

Four concise sentences with no fluff. The purpose is front-loaded in the first sentence, followed by essential details in a logical order. Every sentence adds value.

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?

Given the tool's complexity (async, public toggle, metadata validation) and the existence of an output schema, the description covers the main workflow and prerequisites. It could include error handling or validation details, but it is largely complete for an agent to invoke correctly.

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%, so the description must compensate. It explains the `folder` parameter via the local folder and metadata requirement, `public` via default privacy, and `confirm_token` via the public making condition. Each parameter is contextualized, adding significant meaning beyond names and types.

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 creates a new dataset from a local folder, specifies default privacy, and includes prerequisites. It distinctly focuses on creation, differentiating it from sibling dataset tools like version or delete.

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?

Usage is implied: use for creating new datasets. However, it does not explicitly contrast with alternatives like kaggle_version_dataset for updates, nor does it state when not to use it. The description lacks explicit guidance but is sufficient for basic usage.

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