query_dataset

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

With readOnlyHint already declaring a safe read, the description still adds value by disclosing the return format (JSON array) and the 10,000-row per-call cap, neither of which appears in the annotations. It does not cover ordering, pagination, or error behavior.

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, front-loaded with purpose before the use case and return format. The middle sentence is mildly redundant with the first but not wasteful enough to penalize heavily.

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?

With no output schema and no output-format annotations, the description usefully supplies the return shape and row cap. Given the rich two-level schema for filters, the definition is nearly complete, lacking only result ordering or pagination notes.

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 every parameter (limit, where, select, dataset_id) is already documented in the schema, including operators and value rules. The description adds no parameter-level detail beyond the schema, so the 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 (query) plus resource (queryable dataset) and the outcome (return matching rows). It distinguishes itself somewhat from download-oriented siblings by noting it avoids downloading the full dataset, though it does not name a 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?

The phrase 'useful for extracting a subset without downloading the full dataset' implies a use case but gives no explicit when-to-use guidance or named alternatives (e.g. preview_sample, get_dataset, search_datasets). Usage is inferable rather than stated.

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