Skip to main content
Glama

Discover official datasets

discover
Read-onlyIdempotent

Find what official data is available about a topic.

Use this to explore what datasets exist. It returns catalogue metadata, never observations — and neither do ask and build_url, which prepare an exact source request that still has to be downloaded and queried (fetch / stage_url when the client cannot do that itself).

Two response shapes, and shape says which one arrived.

  • ranked — results lists matching datasets, best first, each with its dimensions, coverage, and the matches that justify it.

  • anchored — topic named one concrete code (a place, a country, an indicator) and nothing forced the ranked path. The answer is then anchor (the code chosen, and what else the topic could have meant), facets (what varies across the datasets publishing it) and anchored_datasets (those datasets, paged by page.next_offset). results is [] on this shape by construction — that is not "nothing found". If the chosen code is wrong, re-query with one of anchor.alternatives[].name.

The two shapes never both appear. Anything that scopes the search is served by the ranked path: agencies, region, user_country, keywords, a non-English language, or an offset past the anchored page. A code also stays ranked when fewer than max(15, limit) datasets publish it (it or a code beneath it), and when resolving it or counting its datasets fails or does not finish in time — that last case, and only it, carries a retrieval_degraded warning with level anchor_unavailable; a retry may then anchor.

Anchored rows are datasets that publish the code or one beneath it — never ones merely permitted to carry it, never ones carrying only its parent.

Two keys explain the rest of the response: _k expands the abbreviated row keys, and _notes explains whatever this particular response happens to contain, keyed by field or field=value.

Common workflow: discover -> inspect -> ask

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": {
      "topic": "<topic>"
    },
    "name": "discover"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoRows to return, default 15. The anchored shape needs a family of at least max(15, limit), so a large limit makes the ranked shape more likely.
topicYesWhat the data is about, in natural language. Naming one concrete code — a country, a city, an indicator — returns the anchored shape when at least max(15, limit) datasets publish it; a retrieval_degraded/anchor_unavailable warning marks a ranked answer whose anchoring failed or timed out.
offsetNoRow offset; pass `page.next_offset` from the previous response. An offset past the anchored page forces the ranked shape.
regionNoGeography the user is asking about; affects coverage ranking, never the agency filter. Forces the ranked shape.
agenciesNoRestrict to these publisher codes (e.g. ["ABS", "OECD"]). Use only when the user names a publisher outright — it hides international sources reporting on a country. For a country use `region`. Forces the ranked shape.
keywordsNoOverride the auto-extracted graph-search terms. Rarely needed. Forces the ranked shape.
languageNoISO search language, default "en". Anything else forces the ranked shape — the anchor name index is English only.en
user_countryNoThe country the USER is in. Pass only when the user has stated where they are; never infer it from the question. This is not the country the question is about — that is `region`. Used to prefer data covering the user's country when the question names no geography of its own. Forces the ranked shape.

Output Schema

NameRequiredDescriptionDefault
_kYesExpands the abbreviated row keys.
pageYes
shapeYesranked: the answer is in `results`. anchored: the answer is in anchor + facets + anchored_datasets, and `results` is [] by construction. Read this first.
_notesNoHow to read what this particular response contains, keyed by field or `field=value`. Only conditions that fired are here, so an absent key means the case did not arise.
anchorNoWhat the response is anchored on, and what else the query could have meant.
facetsNoWhat varies across the datasets publishing the anchor code.
resultsYesRanked datasets, best first. Always [] on the anchored shape — that is not "nothing found"; the answer is in anchor/facets/anchored_datasets.
warningsNo
other_agenciesNoBounded context from sources outside the `agencies` filter. Never displaces a results row.
anchored_datasetsNoDatasets publishing the anchor code, paged by page.next_offset. Pass agency_id + dataflow_id to inspect or build_url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedOutput schema / properties / _k / properties / doc
      Added value: +{
      +  "const": "producer's own documentation page for this dataflow",
      +  "type": "string"
      +}
    • changedOutput schema / properties / _k / required
      Previous value: -[
      -  "desc",
      -  "dim",
      -  "lic"
      -]New value: +[
      +  "desc",
      +  "dim",
      +  "lic",
      +  "doc"
      +]
    • addedOutput schema / properties / other_agencies / items / properties / alternative_dataflows
      Added value: +{
      +  "description": "Optional evidence-backed sibling hints; not exhaustive or ranked replacements.",
      +  "items": {
      +    "description": "A metadata-evidenced sibling to inspect, not a replacement or successor.",
      +    "properties": {
      +      "agency_id": {
      +        "type": "string"
      +      },
      +      "dataflow_id": {
      +        "type": "string"
      +      },
      +      "dataflow_version": {
      +        "type": "string"
      +      },
      +      "evidence": {
      +        "const": "direct_actual_dimension_members",
      +        "type": "string"
      +      },
      +      "note": {
      +        "const": "Inspect definitions before switching; joint series availability is not established.",
      +        "type": "string"
      +      },
      +      "relationship": {
      +        "const": "same_family_identifier_or_name",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "agency_id",
      +      "dataflow_id",
      +      "relationship",
      +      "evidence",
      +      "note"
      +    ],
      +    "title": "DiscoverAlternativeDataflow",
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / other_agencies / items / properties / doc
      Added value: +{
      +  "description": "Producer's own documentation page for this dataset.",
      +  "properties": {
      +    "kind": {
      +      "type": "string"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "origin": {
      +      "const": "derived",
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "url"
      +  ],
      +  "title": "DiscoverDoc",
      +  "type": "object"
      +}
    • addedOutput schema / properties / results / items / properties / alternative_dataflows
      Added value: +{
      +  "description": "Optional evidence-backed sibling hints; not exhaustive or ranked replacements.",
      +  "items": {
      +    "description": "A metadata-evidenced sibling to inspect, not a replacement or successor.",
      +    "properties": {
      +      "agency_id": {
      +        "type": "string"
      +      },
      +      "dataflow_id": {
      +        "type": "string"
      +      },
      +      "dataflow_version": {
      +        "type": "string"
      +      },
      +      "evidence": {
      +        "const": "direct_actual_dimension_members",
      +        "type": "string"
      +      },
      +      "note": {
      +        "const": "Inspect definitions before switching; joint series availability is not established.",
      +        "type": "string"
      +      },
      +      "relationship": {
      +        "const": "same_family_identifier_or_name",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "agency_id",
      +      "dataflow_id",
      +      "relationship",
      +      "evidence",
      +      "note"
      +    ],
      +    "title": "DiscoverAlternativeDataflow",
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / results / items / properties / doc
      Added value: +{
      +  "description": "Producer's own documentation page for this dataset.",
      +  "properties": {
      +    "kind": {
      +      "type": "string"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "origin": {
      +      "const": "derived",
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "url"
      +  ],
      +  "title": "DiscoverDoc",
      +  "type": "object"
      +}
  2. Changed3 schema fields changed
    • addedOutput schema / properties / anchored_datasets / items / properties / period_calendar
      Added value: +{
      +  "const": "buddhist",
      +  "description": "Present ONLY for a Buddhist-Era dataset: TIME_PERIOD, and so any URL's startPeriod/endPeriod, is the Gregorian year + 543 (2567 = 2024). Absent means Gregorian.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / other_agencies / items / properties / period_calendar
      Added value: +{
      +  "const": "buddhist",
      +  "description": "Present ONLY for a Buddhist-Era dataset: TIME_PERIOD, and so any URL's startPeriod/endPeriod, is the Gregorian year + 543 (2567 = 2024). Absent means Gregorian.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / period_calendar
      Added value: +{
      +  "const": "buddhist",
      +  "description": "Present ONLY for a Buddhist-Era dataset: TIME_PERIOD, and so any URL's startPeriod/endPeriod, is the Gregorian year + 543 (2567 = 2024). Absent means Gregorian.",
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • changedInput schema / properties / topic / description
      Previous value: -"What the data is about, in natural language. Naming one concrete code — a country, a city, an indicator — returns the anchored shape."New value: +"What the data is about, in natural language. Naming one concrete code — a country, a city, an indicator — returns the anchored shape when at least max(15, limit) datasets publish it; a retrieval_degraded/anchor_unavailable warning marks a ranked answer whose anchoring failed or timed out."
    • changedOutput schema / properties / warnings / items / properties / level / description
      Previous value: -"Sub-kind of `code`, not a severity ordering (e.g. semantic_unavailable, low_no_match)."New value: +"Sub-kind of `code`, not a severity ordering (e.g. semantic_unavailable, anchor_unavailable, low_no_match)."
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), and the description goes well beyond them: it discloses the two mutually exclusive response shapes, the exact conditions that select each, that an empty `results` under the anchored shape is not "nothing found," and the `retrieval_degraded`/`anchor_unavailable` warning semantics with retry advice. It also explains the `_k` and `_notes` companion keys — behavioral context an agent cannot get from annotations.

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 one-line purpose and the workflow, with the shape mechanics grouped coherently afterward. It is long, but the complexity justifies most of the length; the main waste is restating the "forces the ranked shape" consequence that appears verbatim in six of the schema parameter descriptions.

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?

For an 8-parameter, dual-shape, open-world search tool, nothing an agent needs to call it correctly is missing: it covers shape selection, degradation handling, empty-result interpretation, and recovery via `anchor.alternatives[].name`. The output schema exists, yet the description still makes the non-obvious empty-results case legible, which is the highest-value thing it could add.

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 100%, so the per-parameter meanings are already documented; this is above the baseline 3 because the description adds a cross-parameter rule the schema only states piecemeal — that agencies, region, user_country, keywords, a non-English language, or a past-anchored-page offset all force the ranked path. It also explains the interaction the schema hints at but does not fully reason about: a code stays ranked when fewer than max(15, limit) datasets publish it.

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?

States a specific verb and resource ("Find what official data is available about a topic") and immediately narrows scope with "returns catalogue metadata, never observations." It explicitly distinguishes itself from siblings ask and build_url, which "prepare an exact source request that still has to be downloaded and queried."

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?

"Use this to explore what datasets exist" gives the when, and the closing "Common workflow: discover -> inspect -> ask" plus the fetch/stage_url fallback note place it precisely in the toolchain. Exclusions are explicit: ask and build_url do not return observations either, so an agent knows discovery is the entry point.

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.

Resources