Skip to main content
Glama

Sdmx Dataflow Structure

sdmx_dataflow_structure
Read-onlyIdempotent

Get the structure of one dataflow from any SDMX 2.1 registry: its ordered dimensions and, for each, the valid codes with labels. This answers "what do the codes in dataflow X mean" and "what key do I need to pull data from it", use it before calling a registry-specific get_data tool. Covers eurostat, oecd, ecb, unsd (UN Statistics Division via the data.un.org SDMX hub), imf, bis, ilo, abs. For ILO or ABS dataflows, prefer the ilostat/abs-au packs' own dataflow_structure tool, this one exists mainly for the other six. Example: sdmx_dataflow_structure({ registry: "eurostat", dataflow: "une_rt_m" }) or sdmx_dataflow_structure({ registry: "bis", dataflow: "WS_CBPOL" }).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dataflow": "une_rt_m",
      "registry": "eurostat"
    },
    "name": "sdmx_dataflow_structure"
  }
}

Input Schema

NameRequiredDescriptionDefault
agencyNoOverride the registry's default maintaining agency id, e.g. "OECD.SDD.NAD" for an OECD dataflow published by a specific directorate. Most callers can omit this.
versionNoDataflow version, e.g. "1.0". Defaults to "latest".
dataflowYesDataflow id, e.g. "une_rt_m" (Eurostat), "WS_CBPOL" (BIS), "EER" (IMF). Case usually does not matter but pass it exactly as published.
registryYesWhich SDMX registry to query: eurostat, oecd, ecb, unsd, imf, bis, ilo, abs.
max_codes_per_dimensionNoCap codes returned per dimension (default 50, max 500). Codelists like country or region lists can have thousands of codes.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real context beyond that: the exact set of supported registries (eurostat, oecd, ecb, unsd, imf, bis, ilo, abs) and the fact that codelists can be truncated per dimension. It does not mention rate limits or response size/latency, which would be useful for an open-world remote query.

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?

Front-loaded with the core action and its purpose, then routing guidance, then examples. Every clause is functional, though the registry enumeration and two example invocations make it longer than strictly necessary.

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 compensates by describing the return shape (ordered dimensions, codes with labels) so an agent knows what it will get. Five parameters with full schema coverage plus a clear usage precondition make this adequately complete for a read-only lookup tool.

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%, including per-parameter examples for dataflow ids and the agency override, so the schema already carries parameter meaning. The description adds concrete invocation examples (eurostat/une_rt_m, bis/WS_CBPOL) that illustrate realistic value pairing, but contributes no semantics beyond what the schema documents.

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

Purpose4/5

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

Names a specific verb and resource ("Get the structure of one dataflow") and states concretely what is returned: ordered dimensions and valid codes with labels. It frames the two questions it answers, which makes the tool's role identifiable, but it never contrasts itself directly with the adjacent sdmx_codelist sibling, so the boundary is inferred rather than stated.

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

Usage Guidelines5/5

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

Explicit sequencing guidance: "use it before calling a registry-specific get_data tool." It also gives an exclusion with a named alternative, telling callers to prefer the ilostat/abs-au packs' own dataflow_structure tool for ILO or ABS dataflows and explaining that this one exists for the other six registries.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.