ABS Data (observed)

Get data

get_data

Read-onlyIdempotent

Fetch observations. select maps dimension ids to option codes or labels (several allowed); omitted dimensions match everything. The selection is verified live against ABS before fetching, so a call that succeeds always returns real data. Returns up to maxRows observations (default 500, most recent 12 periods per series unless a period range is given), a summary, and the URL for the complete pull. If an option or combination does not exist you are asked to choose from the valid ones.

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": {
      "table": "<table>"
    },
    "name": "get_data"
  }
}

Input Schema

Name	Required	Description
`lastN`	No	Most recent N observations per series; default 12 when no period is given
`table`	Yes
`firstN`	No
`select`	No	dimension id -> option code or label (or several). Omitted dimensions match everything.
`maxRows`	No	Cap on returned observations
`endPeriod`	No
`startPeriod`	No	e.g. 2020, 2020-Q1, 2020-03

Output Schema

Name	Required	Description
`key`	Yes	The resolved selection as an SDMX key
`rows`	Yes
`table`	Yes
`truncated`	Yes
`provenance`	Yes
`fullDataUrl`	Yes
`periodRange`	Yes
`rowsReturned`	Yes
`seriesMatched`	Yes
`availabilityUrl`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. Beyond that the description discloses real behavior: selection is verified live against ABS before fetching so a successful call always returns real data, truncation defaults (500 rows, most recent 12 periods per series), and that overflow returns a URL for the complete pull.

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 and every sentence carries information about selection, verification, or result capping. Sentences are long with layered parentheticals, which slightly slows parsing but no content is filler.

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?

For a 7-parameter tool with nested `select`, the description covers the hard parts and an output schema exists so return structure need not be spelled out. The remaining gap is not saying how an agent obtains a valid `table` value or dimension ids, which likely requires the sibling discovery tools.

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

Parameters4/5

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

Schema coverage is only 57%, so the description must compensate, and it does for the important cases: it explains `select` as dimension id -> code or label with multiple allowed, and clarifies the `lastN` default of 12 periods applies only when no period range is given. `firstN` and the required `table` parameter are not elaborated, leaving a partial gap.

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?

'Fetch observations' states a specific verb and resource, and the body confirms it targets an ABS table's data cells via live verification. It does not differentiate itself from siblings such as `execute` or `search`, which also touch table data, so an agent must infer the boundary.

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

Usage Guidelines3/5

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

Usage semantics inside the tool are explained (omitted dimensions match everything, several codes per dimension allowed, invalid selections prompt a choice), which is genuinely helpful. But there is no statement of when to prefer this over `execute` or `search_options`, and no mention of needing a table id from `search_tables`/`describe_table` first.

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

All ABS Data (observed) tools Inspect

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.