Skip to main content
Glama
Sign In

Belgium Data Desk

by io.github.vecture-be
OverviewDiscussionsAdmin

Preview the rows of a dataset file

preview_dataset
Read-only

Read the first rows of a dataset's CSV/TSV file directly from the publisher and return the column names, inferred column types, the delimiter and encoding, and up to 20 sample rows as published. Works for datasets whose get_dataset record shows preview_available: true. Reads at most the first 64 KiB of the file, so it shows structure and example values, not totals over the whole file; for those, its analysis block gives the download links, a DuckDB query in the file's own dialect and the domains to allow in a sandbox. Example: {"id":"national:d04b704a-1672-4567-bf0d-9a9452618812","rows":5}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "preview_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesDataset id as returned by search_datasets or get_dataset.
rowsNoNumber of sample rows, default 10.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, and the description adds substantive behavior beyond them: a hard read cap of 64 KiB, the preview_available gate, and the fact that preview data is 'as published' rather than computed. It does not cover failure behavior when preview_available is false, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, followed by the capability limit and the fallback for aggregates, then a compact example. The middle sentence is long and stacks several ideas, but every clause carries information and nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must carry the return-value burden, and it does: it names the returned metadata fields and the sample-row payload. Combined with the 64 KiB scope limit and the preview_available prerequisite, an agent has enough to call it correctly; only error behavior is unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented, including the maximum of 20 and the default of 10. The description restates the 20-row ceiling and gives a worked example with rows:5, but adds no semantics the schema lacks, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: read the first rows of a dataset's CSV/TSV file from the publisher. It enumerates exactly what comes back (column names, inferred types, delimiter, encoding, up to 20 sample rows), which clearly separates it from catalogue and analysis-oriented siblings like get_dataset or search_datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states an explicit precondition ('works for datasets whose get_dataset record shows preview_available: true') and an explicit when-not: it shows structure and example values, not totals over the whole file, pointing the agent to the analysis block for aggregates. It stops short of naming a concrete alternative tool for full-file analysis, so it is clear context without a fully enumerated alternative.

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

All Belgium Data Desk toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources