Validate dataset quality

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

Annotations already declare readOnly, idempotent, and openWorld hints. The description adds meaningful behavioral context by explaining what quality metrics are computed and how the score should influence the decision to consume or retry, without contradicting the 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?

Two sentences, front-loaded with the core purpose and followed by actionable advice. No filler or redundancy; every word contributes to clarity.

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?

With an output schema available, the description does not need to explain return values. It covers the tool's purpose, key inputs (optional schema), and decision process, which is sufficient for an agent to select and invoke the tool appropriately in most contexts.

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 description coverage is 67%, with json_schema and sample_size described. The description adds value by clarifying that json_schema is optional and what role it plays in the score, but it does not explain dataset_id or sample_size beyond the schema. This is adequate but not exceptional.

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 'Score' with a clear resource ('a dataset') and lists concrete quality dimensions (schema pass rate, field completeness, duplicate rate, bot-wall detection). It distinguishes itself from siblings by tying directly to retry_low_quality_run, making its role unambiguous.

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 clear usage context: use it before trusting data, and use the resulting score to decide between consuming or retrying. It names a specific alternative (retry_low_quality_run), but does not explicitly state when not to use the tool versus other siblings like fetch_dataset_items.

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