Skip to main content
Glama

Oecd Query Dataset

oecd_query_dataset
Read-onlyIdempotent

Fetch observations from an OECD dataflow filtered by a dimension key and optional time range. Returns decoded rows (one per observation) with dimension and attribute labels, and values already scaled by the observation unit multiplier. Large multi-country time-series spill to a DataCanvas table — follow up with oecd_dataframe_query; without DataCanvas every row still comes back, but the rendered table stops at a preview slice. Call oecd_get_dataset_info first to learn the dimension order for constructing the key.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesDot-delimited dimension key matching the dimension order from oecd_get_dataset_info. Empty segments are wildcards; "+" separates multiple values per segment. Example: "A.USA+DEU.B1GQ.." — Annual, USA or Germany, GDP, all remaining dimensions.
flow_refYesFull flow reference — e.g. "OECD.SDD.NAD,DSD_NAAG@DF_NAAG_I", or the bare "OECD.TAD.ARP,DF_AEI2024_DASHBOARD" form for a dataflow published without a datastructure prefix. Obtain from oecd_search_datasets and pass it through unchanged.
canvas_idNoCanvas ID from a prior oecd_query_dataset call, to stage this result alongside that one. Omit to let the server mint a canvas if this result needs one — a canvas_id comes back only when the result was large enough to spill, never on a result that fits inline.
end_periodNoEnd of the time range — ISO period code such as "2023" or "2023-Q4". Omit to include up to the latest available period.
start_periodNoStart of the time range — ISO period code such as "2010", "2010-Q1", or "2010-01". Omit to include all history (may produce very large results).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsNoObservation rows. Every row of the result when truncated is absent; the leading preview slice when truncated is true — query the canvas table for the rest.
errorNoPresent when the call failed. Absent on success.
sourceNoData source attribution — always "OECD".
canvas_idNoCanvas handle for the staged result. Present only when DataCanvas is configured and the result exceeded the inline budget; absent when DataCanvas is off, and absent when it is on but the result fit inline. Pass to oecd_dataframe_query or oecd_dataframe_describe.
query_keyNoDimension key used in this query.
row_countNoTotal rows in the result (or on the canvas when truncated).
truncatedNoTrue when rows is a preview slice and the full result was staged on DataCanvas; omitted entirely (never false) when rows holds the complete result. Use oecd_dataframe_query with the canvas_id for analytics over the full set. A complete rows never means a complete rendered table — content_table_capped reports that separately.
table_nameNoCanvas table name holding the full result — present when canvas_id is set.
query_flow_refNoFlow reference used in this query.
query_end_periodNoEnd period filter applied in this query, if any.
content_table_rowsNoRows the rendered table shows when content_table_capped is true.
query_start_periodNoStart period filter applied in this query, if any.
content_table_cappedNoTrue when the rendered table shows only the leading rows of the result. Distinct from truncated: nothing was staged anywhere, and structuredContent.rows still holds every row. To shrink the result itself, name fewer values per key segment or set a narrower start_period / end_period; to reach the full set as a queryable table instead, run with CANVAS_PROVIDER_TYPE=duckdb and follow up with oecd_dataframe_query.

TDQS

A4.7/5.0
Behavior5/5

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

The description adds meaningful behavior beyond the annotations: rows are decoded with labels, values are scaled by the observation unit multiplier, large results spill to DataCanvas, and without DataCanvas every row still returns but the rendered table preview is sliced. No contradiction with the readOnly, openWorld, or idempotent hints.

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

Conciseness5/5

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

Three dense sentences deliver the core action, return behavior, spill handling, and prerequisite in order. Every clause earns its place with no redundancy or fluff.

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

Completeness5/5

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

Given the detailed input schema, annotations, and output schema, the description covers what the tool returns, how result size behaves, what to do for large spills, and what to call beforehand. An agent has enough context to invoke this tool correctly and route to siblings when appropriate.

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% and each parameter already has a detailed explanation, so the description does not need to repeat parameter-level semantics. The main description adds context around result behavior rather than new parameter meaning, which matches the baseline of 3.

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 states a specific verb and resource: it fetches observations from an OECD dataflow filtered by dimension key and optional time range. It differentiates itself from siblings by explicitly naming the prerequisite oecd_get_dataset_info and the follow-up oecd_dataframe_query.

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?

The description gives explicit usage context: call oecd_get_dataset_info first to learn dimension order, and follow up with oecd_dataframe_query when large results spill to a DataCanvas table. This tells an agent when this tool fits into a multi-step workflow versus when another sibling is needed.

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.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool occupies a distinct stage of the OECD data workflow: search/agency discovery, dataset structure, dimension values, observation querying, and SQL analysis of spilled results. The two query tools are differentiated by source (SDMX vs staged DataCanvas tables), and the two metadata tools are differentiated by purpose (key structure vs codelist values).

Naming Consistency4/5

Most tools follow an oecd_<verb>_<noun> pattern (get, list, query, search), and all share the oecd_ prefix and snake_case. The two dataframe tools shift to oecd_dataframe_<verb>, a minor but noticeable ordering deviation.

Tool Count5/5

Seven tools is well-scoped for an OECD data access server: discovery, metadata, dimension values, observation query, and large-result SQL handling. There is no apparent bloat or overly thin coverage.

Completeness5/5

The set covers the full journey from finding datasets and agencies, learning the SDMX key structure, resolving dimension codes, fetching observations, and analyzing spilled datasets with SQL. This is a complete read-only workflow for the domain.