Profile a datasource (stats + sample rows)

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

The annotations already declare readOnlyHint: true and openWorldHint: true, so the description does not need to reiterate side effects. The description itself is transparent about the operation: it samples and returns statistics and rows, implying no modifications. There is no contradiction between the description and annotations, and the description adds detail about the read-only nature by using the verb 'sample'.

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?

The description is verbose and contains redundant phrasing. For example, it repeats 'so you see real column names and literal values in the same call' and then again 'match a block's column constants to reality.' The em-dash style and the extra explanatory sentence ('Exactly what you need...') could be condensed. While not overly long, it lacks conciseness and could be streamlined without losing meaning.

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?

The description thoroughly explains what the tool returns (per-column stats and sample rows) and its purpose. However, it does not mention error scenarios, limits beyond parameter defaults, or how the results are formatted. Since there is no output schema, the description partially compensates by describing the output structure, but it could be more comprehensive regarding edge cases (e.g., empty datasource, large datasets). Overall, it is sufficient for a typical agent interaction.

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?

All four parameters are fully described in the schema with clear meanings: datasource_id, sample_size, sample_rows, and distinct_cap each have detailed descriptions. The schema coverage is 100%, and the descriptions provide sufficient context (e.g., 'Stop counting distinct values past this many per column'). No additional clarification is needed in the tool description beyond what is already provided.

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 clearly states the tool's purpose: sampling a datasource and returning per-column statistics plus raw sample rows. It explicitly lists what is returned (inferred type, non-null/empty counts, distinct value count, sample values, min/max) and explains the benefit ('so you see real column names and literal values'). This is specific and unambiguous, distinguishing it from generic resource inspection tools.

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 includes a clear use case: 'Exactly what you need to design filters, choose chart dimensions, pick aggregations, and match a block's column constants to reality.' This indicates when to use the tool, though it does not explicitly contrast with sibling tools like describe_resource or list_resource. It implies a data profiling context, which is sufficient guidance for an agent to select it appropriately.

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