Skip to main content
Glama

Décrire un jeu de données

describe_dataset
Read-only

Get detailed metadata and column schema for a dataset: title, description, license, topics, row count, geo/temporal coverage and every column with its type, concept and enum values. Call datafair_search_data with size=3 afterwards to see sample rows.

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": {
      "datasetId": "<datasetId>"
    },
    "name": "describe_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
datasetIdYesThe "id" of a datafair_list_account_datasets result, not its title or slug.
response_formatNoconcise: id, slug, title, summary, description, page, count, keywords, origin, license, topics, spatial, temporal, frequency, bbox, timePeriod, publicationSites, schema. detailed: every field.concise

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / datasetId / description
      Previous value: -"The exact dataset ID from the \"id\" field in list_datasets results. Do not use the title or slug."New value: +"The \"id\" of a datafair_list_account_datasets result, not its title or slug."
    • addedInput schema / properties / response_format
      Added value: +{
      +  "default": "concise",
      +  "description": "concise: id, slug, title, summary, description, page, count, keywords, origin, license, topics, spatial, temporal, frequency, bbox, timePeriod, publicationSites, schema. detailed: every field.",
      +  "enum": [
      +    "concise",
      +    "detailed"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / (root)
      Previous value: -{
      -  "$schema": "http://json-schema.org/draft-07/schema#",
      -  "additionalProperties": false,
      -  "properties": {
      -    "bbox": {
      -      "description": "Geographic bounding box [lonMin, latMin, lonMax, latMax]",
      -      "items": {
      -        "type": "number"
      -      },
      -      "type": "array"
      -    },
      -    "count": {
      -      "description": "Total number of data rows in the dataset",
      -      "type": "number"
      -    },
      -    "description": {
      -      "description": "A markdown description of the dataset content",
      -      "type": "string"
      -    },
      -    "frequency": {
      -      "description": "Update frequency of the dataset",
      -      "type": "string"
      -    },
      -    "geolocalized": {
      -      "description": "Whether the dataset has geographic data",
      -      "type": "boolean"
      -    },
      -    "id": {
      -      "description": "Unique dataset Id (required for search_data tools)",
      -      "type": "string"
      -    },
      -    "keywords": {
      -      "description": "Keywords associated with the dataset",
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    "license": {
      -      "additionalProperties": false,
      -      "description": "Dataset license information (must be included in responses)",
      -      "properties": {
      -        "href": {
      -          "description": "URL to the license text",
      -          "type": "string"
      -        },
      -        "title": {
      -          "description": "License name/title",
      -          "type": "string"
      -        }
      -      },
      -      "required": [
      -        "href",
      -        "title"
      -      ],
      -      "type": "object"
      -    },
      -    "origin": {
      -      "description": "Source or provider of the dataset",
      -      "type": "string"
      -    },
      -    "page": {
      -      "description": "Link to the dataset page (must be included in responses as citation source)",
      -      "type": "string"
      -    },
      -    "sampleLines": {
      -      "description": "Array of 3 sample data rows showing real values from the dataset. Use these examples to understand exact formatting, casing, and typical values for _eq and _search filters.",
      -      "items": {
      -        "additionalProperties": {},
      -        "type": "object"
      -      },
      -      "type": "array"
      -    },
      -    "schema": {
      -      "description": "Dataset column schema with types and metadata",
      -      "items": {
      -        "additionalProperties": false,
      -        "properties": {
      -          "concept": {
      -            "description": "Semantic concept associated with the column",
      -            "type": "string"
      -          },
      -          "description": {
      -            "description": "Column description",
      -            "type": "string"
      -          },
      -          "enum": {
      -            "description": "List of all possible values for this column",
      -            "type": "array"
      -          },
      -          "enumTotal": {
      -            "description": "Total number of enum values before truncation",
      -            "type": "number"
      -          },
      -          "enumTruncated": {
      -            "description": "Whether the enum list was truncated because it exceeded 20 values",
      -            "type": "boolean"
      -          },
      -          "key": {
      -            "description": "Column identifier",
      -            "type": "string"
      -          },
      -          "labels": {
      -            "additionalProperties": {
      -              "type": "string"
      -            },
      -            "description": "Object mapping actual data values (keys) to human-readable labels (values). Use keys for filters.",
      -            "type": "object"
      -          },
      -          "title": {
      -            "description": "Human-readable column title",
      -            "type": "string"
      -          },
      -          "type": {
      -            "description": "Data type of the column",
      -            "type": "string"
      -          }
      -        },
      -        "required": [
      -          "key",
      -          "type"
      -        ],
      -        "type": "object"
      -      },
      -      "type": "array"
      -    },
      -    "slug": {
      -      "description": "Human-readable unique identifier for the dataset, used in URLs",
      -      "type": "string"
      -    },
      -    "spatial": {
      -      "description": "Spatial coverage information"
      -    },
      -    "summary": {
      -      "description": "A brief summary of the dataset content",
      -      "type": "string"
      -    },
      -    "temporal": {
      -      "description": "Temporal coverage information"
      -    },
      -    "temporalDataset": {
      -      "description": "Whether the dataset has temporal data",
      -      "type": "boolean"
      -    },
      -    "timePeriod": {
      -      "additionalProperties": false,
      -      "description": "Time period covered by the dataset",
      -      "properties": {
      -        "endDate": {
      -          "description": "End date of the time period",
      -          "type": "string"
      -        },
      -        "startDate": {
      -          "description": "Start date of the time period",
      -          "type": "string"
      -        }
      -      },
      -      "required": [
      -        "startDate",
      -        "endDate"
      -      ],
      -      "type": "object"
      -    },
      -    "title": {
      -      "description": "Dataset title",
      -      "type": "string"
      -    },
      -    "topics": {
      -      "description": "Topics/categories the dataset belongs to",
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    }
      -  },
      -  "required": [
      -    "id",
      -    "title",
      -    "page",
      -    "count",
      -    "schema",
      -    "sampleLines"
      -  ],
      -  "type": "object"
      -}New value: +null
  2. Changed10 schema fields changed
    • changedInput schema / properties / datasetId / description
      Previous value: -"The exact dataset ID from the \"id\" field in search_datasets results. Do not use the title or slug."New value: +"The exact dataset ID from the \"id\" field in list_datasets results. Do not use the title or slug."
    • changedOutput schema / properties / bbox / description
      Previous value: -"Spatial bounding box of the dataset: [lonMin, latMin, lonMax, latMax]. Present only for geolocalized datasets."New value: +"Geographic bounding box [lonMin, latMin, lonMax, latMax]"
    • changedOutput schema / properties / geolocalized / description
      Previous value: -"Whether this dataset has geographic data. When true, geo filters (bbox, geoDistance) are available in search_data, aggregate_data, and calculate_metric."New value: +"Whether the dataset has geographic data"
    • removedOutput schema / properties / link
      Removed value: -{
      -  "description": "Link to the dataset page (must be included in responses as citation source)",
      -  "type": "string"
      -}
    • addedOutput schema / properties / page
      Added value: +{
      +  "description": "Link to the dataset page (must be included in responses as citation source)",
      +  "type": "string"
      +}
    • changedOutput schema / properties / temporalDataset / description
      Previous value: -"Whether this dataset has temporal data (date fields). When true, the dateMatch filter is available in search_data, aggregate_data, and calculate_metric."New value: +"Whether the dataset has temporal data"
    • changedOutput schema / properties / timePeriod / description
      Previous value: -"Temporal coverage of the dataset data. Present only for temporal datasets."New value: +"Time period covered by the dataset"
    • changedOutput schema / properties / timePeriod / properties / endDate / description
      Previous value: -"End of the temporal coverage (ISO datetime)"New value: +"End date of the time period"
    • changedOutput schema / properties / timePeriod / properties / startDate / description
      Previous value: -"Start of the temporal coverage (ISO datetime)"New value: +"Start date of the time period"
    • changedOutput schema / required
      Previous value: -[
      -  "id",
      -  "title",
      -  "link",
      -  "count",
      -  "schema",
      -  "sampleLines"
      -]New value: +[
      +  "id",
      +  "title",
      +  "page",
      +  "count",
      +  "schema",
      +  "sampleLines"
      +]
  3. Changed4 schema fields changed
    • addedOutput schema / properties / bbox
      Added value: +{
      +  "description": "Spatial bounding box of the dataset: [lonMin, latMin, lonMax, latMax]. Present only for geolocalized datasets.",
      +  "items": {
      +    "type": "number"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / geolocalized
      Added value: +{
      +  "description": "Whether this dataset has geographic data. When true, geo filters (bbox, geoDistance) are available in search_data, aggregate_data, and calculate_metric.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / temporalDataset
      Added value: +{
      +  "description": "Whether this dataset has temporal data (date fields). When true, the dateMatch filter is available in search_data, aggregate_data, and calculate_metric.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / timePeriod
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Temporal coverage of the dataset data. Present only for temporal datasets.",
      +  "properties": {
      +    "endDate": {
      +      "description": "End of the temporal coverage (ISO datetime)",
      +      "type": "string"
      +    },
      +    "startDate": {
      +      "description": "Start of the temporal coverage (ISO datetime)",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "startDate",
      +    "endDate"
      +  ],
      +  "type": "object"
      +}
  4. Changed2 schema fields changed
    • addedOutput schema / properties / schema / items / properties / enumTotal
      Added value: +{
      +  "description": "Total number of enum values before truncation",
      +  "type": "number"
      +}
    • addedOutput schema / properties / schema / items / properties / enumTruncated
      Added value: +{
      +  "description": "Whether the enum list was truncated because it exceeded 20 values",
      +  "type": "boolean"
      +}
  5. Changed1 schema field changed
    • changedInput schema / properties / datasetId / description
      Previous value: -"The unique dataset ID obtained from search_datasets or provided by the user"New value: +"The exact dataset ID from the \"id\" field in search_datasets results. Do not use the title or slug."
  6. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value by disclosing the shape of the returned metadata, but says nothing about cost, size limits, or failure modes when the datasetId is unknown or inaccessible.

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?

Two tight sentences: the return scope is front-loaded and the follow-up step is clearly appended. No redundant restatement of the name or title.

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 enumeration of returned fields does the work of explaining what comes back, and the schema fully documents both inputs. The only shortfall is the absence of guidance on how this relates to the metadata-ish siblings and on the discrepancy between "concise" and "detalled" payloads relative to the stated field list.

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 the schema already explains that datasetId must come from datafair_list_account_datasets rather than a title or slug, plus the concise/detailed enum tradeoff. The description contributes nothing about either parameter, so the baseline of 3 applies.

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?

The description opens with a specific verb and resource ("Get detailed metadata and column schema for a dataset") and enumerates the returned content (title, license, topics, row count, coverage, column types/concepts/enums). It never names a sibling tool to contrast with, so an agent must infer the difference from list_datasets or get_field_values on its own.

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?

There is useful sequencing guidance ("Call datafair_search_data with size=3 afterwards to see sample rows"), which tells the agent this is a metadata-first step. However, there is no statement of when to pick this over list_datasets or get_field_values, and the named follow-up tool does not match any sibling name exactly.

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