Misata Studio: verified synthetic data

Most tools map to distinct stages of the synthetic-data workflow: plan, validate, generate, monitor, query, export, and inspect. A few pairs require careful reading to distinguish, notably generate_dataset vs start_generation (sync vs async) and check_answers vs get_certificate (answer checking vs certification/answer key).

The set follows a mostly consistent snake_case verb_noun convention: generate_dataset, query_dataset, export_dataset, validate_blueprint, cancel_generation. Minor deviations are blueprint_guide and whoami, which are noun/reference-style names rather than verb-led actions.

Thirteen tools is well-scoped for a platform covering dataset planning, generation, validation, querying, export, certification, and account introspection. Each tool appears to earn its place, with the async lifecycle tools justified by long-running generation jobs.

The surface is broad and covers the main lifecycle from discovery and planning through generation, validation, querying, export, and answer checking. Minor gaps exist around managing generated datasets, such as listing or deleting existing datasets, but agents can work around this given the temporary dataset retention model.