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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavioral context: the protected split's contents are deliberately withheld, which is important to know before calling this on a protected dataset.

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 tight sentences: what it returns, the hard constraint on contents, then the questions it answers. Front-loaded and waste-free, though the question pair is slightly rhetorical padding.

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, but the description summarizes the return shape (counts, coverage, hashes) and the withholding rule, so the agent knows what to expect. For a two-parameter read-only listing, that is nearly everything needed.

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%, with datasetId and the superadmin-only customerId both documented in the schema. The description adds no syntax or format detail about either parameter, so the baseline of 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 resource and what it returns: frozen dataset versions exposed as counts, template coverage, and hashes. It implicitly separates itself from list_dataset_examples by declaring the examples are never returned, though it does not name that sibling directly.

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?

Gives concrete framing questions — 'is there a frozen version to train on?' and 'is it training-eligible?' — which tell the agent when this tool is the right call. It stops short of naming exclusions or pointing to a specific alternative tool.

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