create_dataset

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

Since annotations are none, the description carries the burden. It mentions 'Copies logs asynchronously' for the source_dataset_id, which is a key behavioral note. However, it doesn't disclose other behaviors like whether sampling creates an asynchronous job, or how long operations might take, but it adds some transparency.

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 extremely concise and well-structured. It uses a MODES bullet list with actionable phrases, front-loads the purpose, and every sentence earns its place. No fluff.

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 (multiple modes, 8 params, nested objects) and lack of annotations, the description is reasonably complete. It explains the three creation methods, but lacks details like example behaviors or error conditions. However, for a create tool without output schema, it's adequate.

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 100%, so baseline is 3. The description adds value by grouping parameters into modes: 'pass is_empty=true' clarifies that name might not be required when duplicating, 'sampling (1-100)' adds range, and 'initial_log_filters' is explained with an example. This goes beyond the schema.

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: 'Create a new dataset.' It then breaks down three distinct modes (empty, sampled, duplicate) with specific parameters, which distinguishes it from siblings like 'list_datasets', 'get_dataset', and 'update_dataset'.

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 MODES section provides explicit guidance on when to use each mode, including required parameters (e.g., 'pass is_empty=true' for empty, 'pass start_time, end_time' for sampled). While it doesn't explicitly say when NOT to use this tool or mention alternatives, the mode breakdown gives clear context.

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