Dataset Render Preview

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

readOnlyHint=true already tells the agent this is non-mutating, so the description only needs to add context. It does add one useful behavioral fact: no training job is submitted as a side effect. Beyond that it says nothing about cost, latency, or what the preview contains.

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?

A single front-loaded sentence with no filler; the core action and the key constraint both land in the first clause.

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, so return values need not be described, but with five undocumented parameters and no schema descriptions the agent cannot tell which inputs are required, what 'renderer' selects, or how to choose between plan_id and dataset. The description is far too thin for a tool with this many knobs.

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% across five parameters, so the description carries the full burden and fails it. It never explains model, dataset, plan_id, renderer, or sample_size, nor how plan_id relates to dataset (the only hint anywhere is the nested 'path' description in 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 (preview) and a specific resource (Cookbook rendering and loss masks), which is enough to distinguish it from mutation-oriented siblings like train_sft or training_start. It does not, however, differentiate itself from neighboring read/inspect tools such as dataset_inspect or dataset_validate.

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 phrase 'without submitting training' implies the intended context: use this to sanity-check data before committing to a training run. That is only implied, not stated as explicit when-to-use guidance, and no alternative tool (dataset_inspect, dataset_validate) is named or excluded.

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