export_dataset

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

No annotations are present, so the description carries the full behavioral burden. It does so well: it discloses that the data is returned inline as text, that parquet is base64-encoded because this is not a file-download channel, and that there is a hard cap of 5000 rows regardless of the requested limit. These are non-obvious runtime characteristics an agent needs to know before calling.

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 sentences deliver the purpose, the unusual output behavior, and the fallback path – all in a front-loaded, focused structure. Every sentence earns its place and there is no filler.

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 annotations, the description still covers the return format, encoding nuance, row cap, and a pagination alternative. The schema covers parameter specifics, so the description is complete enough for an agent to invoke the tool correctly and set expectations.

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 high at 83%, and each parameter already has a meaningful schema-level description. The tool description does not materially extend parameter semantics beyond what the schema already documents, so the baseline of 3 is appropriate.

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 states a specific action ('export rows') applied to a concrete resource ('a dataset') and explicitly enumerates the supported serialization formats (csv, json, geojson, parquet). It also distinguishes this from sibling tools by naming query_records as the alternative for larger datasets, so an agent can select it without opening every schema.

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?

It gives clear when-to-use and when-not-to-use guidance: use this for exporting, and for larger datasets either narrow with where/select or switch to query_records with offset-based pagination. This directly addresses the main selection ambiguity among the sibling tools.

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