Validate DataLens dataset

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the safety profile is covered. The description adds real behavioral value the annotations don't: the reply shape (code, message, dataset_errors) and the stale-revision refusal condition.

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?

Three short sentences with the no-save guarantee front-loaded and no padding. Efficient and well ordered, though the final clause is terse enough to need a second read.

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?

No output schema exists, but the description compensates by naming the three response fields, and it explains the no-persistence and revision constraints. The nested data object's shape is deferred to schema_get (documented in the schema, not the description), leaving a minor gap.

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 100%, so the schema already documents all four parameters, including the pointer to DatasetValidate via schema_get. The description reinforces the 'as last read' freshness expectation for the data payload but adds no field-level syntax beyond the schema; baseline 3 applies.

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 and resource ('Check a dataset, or changes to it') and adds the key scope qualifier 'without saving anything,' which cleanly separates it from datalens_datasets_update/create. An agent can identify this as a dry-run validation without opening the schema.

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?

Strong implied usage: validate before persisting, and the revision-freshness rule ('after a save, content of an older revision is refused') tells the agent exactly when a call will fail. No sibling is named as an explicit alternative (e.g., datalens_datasets_get), so it falls just short of 5.

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