Get dataset schema

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

With no annotations, the description carries the full disclosure burden. It adds useful behavioral context: the schema is inferred from a sample (implying it may be approximate) and the tool is intentionally cheaper than fetching full items. However, it does not describe the output format, warn that sampling may miss rare fields, or mention any error conditions or caveats about inference reliability.

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?

Two sentences, both load-bearing. The first states the function, the second states the use case and the alternative approach to avoid. No filler, no repetition of schema information, and the most important information (what it does) is front-loaded.

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?

For a low-complexity tool (2 params, 1 required) the core is covered. But with no output schema and no annotations, the description could usefully state what the returned schema contains (e.g., field names and types) and explicitly note that a sample-based schema may be incomplete for heterogeneous datasets. These gaps leave the agent partially guessing about the result's reliability and shape.

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 must compensate. It does add meaning: 'from a sample of its items' explains the role of sampleSize, and the dataset context clarifies datasetId. However, it never explicitly ties sampleSize to the sampling behavior or explains the accuracy/cost tradeoff, leaving the agent to infer the parameter's impact from the default and bounds 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?

The description uses a specific verb ('infer'), a clear resource ('the shape of a dataset'), and a concrete mechanism ('from a sample of its items'). It differentiates itself from siblings: the phrase 'instead of pulling whole items to find out' implicitly distinguishes it from get-dataset-items, and 'requesting them via fields' shows it's a lightweight discovery step rather than a data-fetching or metadata-fetching tool like get-dataset.

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 description gives an explicit when-to-use: 'learn which fields exist before requesting them via fields'. It also signals the negative case ('instead of pulling whole items to find out'), which steers the agent away from the heavier alternative. However, it never names the alternative tool (get-dataset-items) or states a clear when-not-to-use condition, so it stops just short of the explicit-exclusion bar.

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