Check a dataset for the tells of synthetic data

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds genuinely useful behavioural context: it works on data from any generator including hand-written scripts, requires no reference dataset, and its findings should be fixed in the schema (lognormal, sampling, null_rate) rather than in rows.

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?

Front-loaded with the core purpose and the sibling contrast before the long enumeration of tells. The tells list is verbose but each entry is a distinct detectable pattern that informs what the tool reports; the fix-a-finding and skip guidance are dense and value-bearing.

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?

An output schema exists, yet the description still orients the agent with the return shape (score, passed, counts, tells with check/table/column/status/evidence). Combined with the usage routing, remediation hints and parameter definitions, nothing needed to call it correctly is missing.

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 0%, so the description carries the load. It defines dataset_dir as 'Directory with one CSV per table (the output_dir from generate_from_schema)' and skip as check names to omit, with a concrete example (["too_clean"]). Both parameters gain meaning absent from 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?

States a specific verb+resource ('find the statistical shapes that make a dataset look generated') and immediately differentiates itself from the sibling audit_dataset by contrasting contradictions vs. shape anomalies. The enumerated tells make the scope unmistakable.

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?

Explicitly names the alternative ('Where audit_dataset finds contradictions, this finds shapes...') and states the precondition (no real data to compare against). It also tells the agent when to pass skip ('tells that are intended, a randomised A/B split is balanced on purpose') and even routes remediation to the schema rather than the rows.

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