Skip to main content
Glama

Get GDELT Coverage Timeline

gdelt_get_coverage_timeline
Read-only

Retrieve a time series showing when news coverage of a topic spiked, or how average tone shifted over time. Use mode "volume" for normalized coverage intensity (% of all global coverage per timestep). Use "volume_raw" for distinct matching-article counts per timestep and norm, the unsmoothed monitored-article denominator; smoothed counts are moving averages. Use mode "volume_with_articles" for the same signal plus the top articles that drove each spike — this is the primary signal-detection mode: a single call reveals both the spike and its cause, avoiding a follow-up gdelt_search_articles call. Use mode "tone" for average sentiment score per timestep (negative = hostile/fearful, positive = celebratory). Date resolution is inferred from returned intervals: 15 minutes or hours for short windows, days for longer ones. In volume_with_articles mode each timestep carries its first 3 article links and referenceCount, the number of references GDELT supplied (up to ten), not all matching articles; name timesteps' dates in points to get only those timesteps, each with its full supplied list. A response carries limit timesteps (default 10, cap 400); when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Explicit startDatetime/endDatetime windows may predate the last 3 months in "volume" and "tone" modes; "volume_raw" and "volume_with_articles" cover only the last 3 months.

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": {
      "query": "<query>"
    },
    "name": "gdelt_get_coverage_timeline"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoTimeline mode: "volume" returns normalized coverage % per timestep, "volume_raw" returns distinct matching-article counts (moving averages when smoothed) and the unsmoothed monitored denominator norm, "volume_with_articles" returns volume plus top articles per spike (best for signal detection), "tone" returns average sentiment score per timestep.volume
limitNoMaximum timesteps per page (default 10, cap 400). Larger counts clamp with limitClamp; strict deployments reject them.
queryYesSearch query using GDELT syntax. Same operators as gdelt_search_articles: phrases, boolean OR, sourcecountry:, sourcelang:, domain:, theme: (GKG theme identifiers come from gdelt_search_themes), tone<.
offsetNoZero-based timestep offset — into the timeline, or into the timesteps named in points. Pass nextOffset from the preceding response, with otherwise identical inputs, to get the next page.
pointsNoTimestep dates to return alone, e.g. ["2024-01-05T12:00:00Z"]. Take them verbatim from series[].data[].date in a prior response, or from the list an unknown_point error prints. The response then carries only these timesteps, in timeline order, and in volume_with_articles mode each carries its complete article list instead of the first 3. A date matching no timestep is rejected rather than silently ignored.
timespanNoTime window relative to now, minimum "15min"; other examples: "24h", "7d", "1m". Ignored when startDatetime/endDatetime are set. Maximum 3 months.
smoothingNoTrailing moving-average width in timesteps (0–30; 0 or 1 leaves values unsmoothed). Width N needs N source steps, omitting leading steps without a full window and potentially shifting peaks later.
endDatetimeNoEnd datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240131235959). Must pair with startDatetime; supplying only one of the two is rejected. In "volume" and "tone" modes the window may predate the last 3 months; "volume_raw" and "volume_with_articles" cover only the last 3 months.
startDatetimeNoStart datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240101000000). Must pair with endDatetime; supplying only one of the two is rejected. In "volume" and "tone" modes the window may predate the last 3 months; "volume_raw" and "volume_with_articles" cover only the last 3 months.

Output Schema

NameRequiredDescriptionDefault
modeNoTimeline mode used for this response.
errorNoPresent when the call failed. Absent on success.
noticeNoGuidance when the query matched no coverage in the window — how to broaden the query or extend the window — or, when this response is one page of several, which timesteps it returned out of how many. When the server's local GKG mirror answered (source: gkg_mirror), why, and how its figures differ from the DOC API's. Absent when the DOC API answered and the whole timeline fit in one response.
seriesNoOne or more time series (typically one for volume/tone), holding the timesteps of this page.
sourceNoWhere this answer came from: doc_api, the GDELT DOC API, or gkg_mirror, the server's local mirror of GDELT's Global Knowledge Graph, which answers when the DOC API refuses the request or returns nothing. Present on every answer while the server runs a mirror; absent otherwise.
attemptsNoEach source tried for this call, in order. Present only when the DOC API did not answer with data and the mirror was consulted.
coverageNoPresent only when the mirror answered less than the requested window. Every count, share, and article in this response comes from answeredStart through answeredEnd; nothing outside it, or in a missing slot, was counted.
limitClampNoPresent only when the requested count exceeded the per-call cap: the call ran exactly as a call at the cap, and every count, notice, and continuation in this response reflects the applied value.
nextOffsetNoOffset of the next page, for the same inputs. Absent when this page reaches the last timestep.
totalCountNoTotal number of data points across all series of the full timeline, not this page.
endDatetimeNoEchoed end datetime when provided (YYYYMMDDHHMMSS).
staleResponseNoPresent only when the refetch of this exact request was refused, failed, or came back empty, and the response is GDELT's stored answer from fetchedAt instead. It holds nothing published after fetchedAt; a relative timespan covers the window ending at fetchedAt, not now. Absent on a live answer.
startDatetimeNoEchoed start datetime when provided (YYYYMMDDHHMMSS).
dateResolutionNoTemporal resolution of the data points — 15min, hour, or day — inferred from the spacing of the returned timesteps. Omitted when fewer than two distinct timesteps came back.
effectiveQueryNoEchoed query string for use in follow-up calls.
expandedPointsNoTimestep dates this response is restricted to, each carrying its full article list — echoing the points input. Omitted when points was not supplied.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum timesteps per page (default 10, cap 400). Larger counts clamp to 400 unless GDELT_CLAMP_LIMITS=false."New value: +"Maximum timesteps per page (default 10, cap 400). Larger counts clamp with limitClamp; strict deployments reject them."
  2. Changed7 schema fields changed
    • changedInput schema / properties / endDatetime / description
      Previous value: -"End datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240131235959). Must pair with startDatetime; supplying only one of the two is rejected."New value: +"End datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240131235959). Must pair with startDatetime; supplying only one of the two is rejected. In \"volume\" and \"tone\" modes the window may predate the last 3 months; \"volume_raw\" and \"volume_with_articles\" cover only the last 3 months."
    • changedInput schema / properties / startDatetime / description
      Previous value: -"Start datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240101000000). Must pair with endDatetime; supplying only one of the two is rejected."New value: +"Start datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240101000000). Must pair with endDatetime; supplying only one of the two is rejected. In \"volume\" and \"tone\" modes the window may predate the last 3 months; \"volume_raw\" and \"volume_with_articles\" cover only the last 3 months."
    • addedOutput schema / properties / attempts
      Added value: +{
      +  "description": "Each source tried for this call, in order. Present only when the DOC API did not answer with data and the mirror was consulted.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One source's outcome for this call.",
      +    "properties": {
      +      "detail": {
      +        "description": "Why, when the outcome has a reason: DOC's failure message or the mirror's.",
      +        "type": "string"
      +      },
      +      "outcome": {
      +        "description": "What the source did: answered, empty (answered with no matches), rate_limited, or unavailable; or why the mirror could not answer: not_ready (no completed sync), not_compiled (the query or its timespan is in a form the mirror cannot evaluate), outside_coverage (the window lies outside the days it holds), store_error.",
      +        "enum": [
      +          "answered",
      +          "empty",
      +          "rate_limited",
      +          "unavailable",
      +          "not_ready",
      +          "not_compiled",
      +          "outside_coverage",
      +          "store_error"
      +        ],
      +        "type": "string"
      +      },
      +      "source": {
      +        "description": "The source tried.",
      +        "enum": [
      +          "doc_api",
      +          "gkg_mirror"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "source",
      +      "outcome"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / coverage
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Present only when the mirror answered less than the requested window. Every count, share, and article in this response comes from answeredStart through answeredEnd; nothing outside it, or in a missing slot, was counted.",
      +  "properties": {
      +    "answeredEnd": {
      +      "description": "End of the window the mirror answered, ISO 8601 UTC.",
      +      "type": "string"
      +    },
      +    "answeredStart": {
      +      "description": "Start of the window the mirror answered, ISO 8601 UTC.",
      +      "type": "string"
      +    },
      +    "missingSlots": {
      +      "description": "15-minute GKG slots inside the answered window that the mirror holds no data for.",
      +      "type": "number"
      +    },
      +    "requestedEnd": {
      +      "description": "End of the requested window, ISO 8601 UTC.",
      +      "type": "string"
      +    },
      +    "requestedStart": {
      +      "description": "Start of the requested window, ISO 8601 UTC.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "requestedStart",
      +    "requestedEnd",
      +    "answeredStart",
      +    "answeredEnd",
      +    "missingSlots"
      +  ],
      +  "type": "object"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when the query matched no coverage in the window — how to broaden the query or extend the window — or, when this response is one page of several, which timesteps it returned out of how many. Absent when the whole timeline fit in one response."New value: +"Guidance when the query matched no coverage in the window — how to broaden the query or extend the window — or, when this response is one page of several, which timesteps it returned out of how many. When the server's local GKG mirror answered (source: gkg_mirror), why, and how its figures differ from the DOC API's. Absent when the DOC API answered and the whole timeline fit in one response."
    • addedOutput schema / properties / source
      Added value: +{
      +  "description": "Where this answer came from: doc_api, the GDELT DOC API, or gkg_mirror, the server's local mirror of GDELT's Global Knowledge Graph, which answers when the DOC API refuses the request or returns nothing. Present on every answer while the server runs a mirror; absent otherwise.",
      +  "enum": [
      +    "doc_api",
      +    "gkg_mirror"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / staleResponse
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Present only when the refetch of this exact request was refused, failed, or came back empty, and the response is GDELT's stored answer from fetchedAt instead. It holds nothing published after fetchedAt; a relative timespan covers the window ending at fetchedAt, not now. Absent on a live answer.",
      +  "properties": {
      +    "ageSeconds": {
      +      "description": "Age of the stored answer when served, in whole seconds.",
      +      "type": "number"
      +    },
      +    "fetchedAt": {
      +      "description": "ISO 8601 time GDELT returned the stored answer.",
      +      "type": "string"
      +    },
      +    "reason": {
      +      "description": "Why the refetch was not used: GDELT rate-limited it, did not answer with data, or answered empty — which GDELT also does under load.",
      +      "enum": [
      +        "gdelt_rate_limited",
      +        "gdelt_unavailable",
      +        "gdelt_empty"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "fetchedAt",
      +    "ageSeconds",
      +    "reason"
      +  ],
      +  "type": "object"
      +}
  3. Changed11 schema fields changed
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 10,
      +  "description": "Maximum timesteps per page (default 10, cap 400). Larger counts clamp to 400 unless GDELT_CLAMP_LIMITS=false.",
      +  "minimum": 1,
      +  "multipleOf": 1,
      +  "type": "number"
      +}
    • changedInput schema / properties / mode / description
      Previous value: -"Timeline mode: \"volume\" returns normalized coverage % per timestep, \"volume_with_articles\" returns volume plus top articles per spike (best for signal detection), \"tone\" returns average sentiment score per timestep."New value: +"Timeline mode: \"volume\" returns normalized coverage % per timestep, \"volume_raw\" returns distinct matching-article counts (moving averages when smoothed) and the unsmoothed monitored denominator norm, \"volume_with_articles\" returns volume plus top articles per spike (best for signal detection), \"tone\" returns average sentiment score per timestep."
    • changedInput schema / properties / mode / enum
      Previous value: -[
      -  "volume",
      -  "volume_with_articles",
      -  "tone"
      -]New value: +[
      +  "volume",
      +  "volume_raw",
      +  "volume_with_articles",
      +  "tone"
      +]
    • changedInput schema / properties / smoothing / description
      Previous value: -"Smoothing window in timesteps (0 = none, 1–5 = moving average width). Reduces noise for spotty topics."New value: +"Trailing moving-average width in timesteps (0–30; 0 or 1 leaves values unsmoothed). Width N needs N source steps, omitting leading steps without a full window and potentially shifting peaks later."
    • changedInput schema / properties / smoothing / maximum
      Previous value: -5New value: +30
    • addedOutput schema / properties / limitClamp
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Present only when the requested count exceeded the per-call cap: the call ran exactly as a call at the cap, and every count, notice, and continuation in this response reflects the applied value.",
      +  "properties": {
      +    "applied": {
      +      "description": "The per-call cap the call ran with instead.",
      +      "type": "number"
      +    },
      +    "parameter": {
      +      "description": "The count input that was clamped.",
      +      "enum": [
      +        "maxRecords",
      +        "limit"
      +      ],
      +      "type": "string"
      +    },
      +    "requested": {
      +      "description": "The value the call asked for.",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "parameter",
      +    "requested",
      +    "applied"
      +  ],
      +  "type": "object"
      +}
    • changedOutput schema / properties / mode / enum
      Previous value: -[
      -  "volume",
      -  "volume_with_articles",
      -  "tone"
      -]New value: +[
      +  "volume",
      +  "volume_raw",
      +  "volume_with_articles",
      +  "tone"
      +]
    • addedOutput schema / properties / series / items / properties / data / items / properties / norm
      Added value: +{
      +  "description": "Total articles monitored at this timestep, unsmoothed even when value is smoothed. Present only in volume_raw mode.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / series / items / properties / data / items / properties / referenceCount / description
      Previous value: -"How many articles GDELT returned for this timestep; articles carries the first 3 unless the timestep was named in points. Present whenever articles is."New value: +"Number of article references GDELT supplied for this timestep (up to ten), not all matching articles; articles carries the first 3 unless the timestep was named in points. Present whenever articles is."
    • changedOutput schema / properties / series / items / properties / data / items / properties / value / description
      Previous value: -"Normalized coverage % (volume mode) or average tone score (tone mode). Tone range is approximately -100 to +100."New value: +"Normalized coverage % (volume or volume_with_articles), distinct matching-article count (volume_raw; a moving average when smoothed), or average tone score (tone mode). Tone range is approximately -100 to +100."
    • addedOutput schema / properties / series / items / properties / peak / properties / norm
      Added value: +{
      +  "description": "Unsmoothed monitored-article denominator at the peak in volume_raw mode.",
      +  "type": "number"
      +}
  4. Changed14 schema fields changed
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Zero-based timestep offset — into the timeline, or into the timesteps named in points. Pass nextOffset from the preceding response, with otherwise identical inputs, to get the next page.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / points / description
      Previous value: -"Timestep dates whose complete article list should be rendered in the text surface, e.g. [\"2024-01-05T12:00:00Z\"]. Take them verbatim from series[].data[].date in a prior response, or from the list an unknown_point error prints. Only affects volume_with_articles rendering — every timestep already carries its full article list in structuredContent regardless. Timesteps not named here show their first 3 links; a date matching no timestep is rejected rather than silently ignored."New value: +"Timestep dates to return alone, e.g. [\"2024-01-05T12:00:00Z\"]. Take them verbatim from series[].data[].date in a prior response, or from the list an unknown_point error prints. The response then carries only these timesteps, in timeline order, and in volume_with_articles mode each carries its complete article list instead of the first 3. A date matching no timestep is rejected rather than silently ignored."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `unknown_point`: A date passed in the points input matches no timestep in a non-empty timeline. `invalid_date_range`: Only one of startDatetime / endDatetime was supplied, one of them is not a real UTC calendar timestamp, or startDatetime is not earlier than endDatetime. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `unknown_point`: A date passed in the points input matches no timestep in a non-empty timeline. `offset_out_of_range`: The requested offset is at or beyond the last timestep of a non-empty timeline, or of the timesteps named in points. `invalid_date_range`: Only one of startDatetime / endDatetime was supplied, one of them is not a real UTC calendar timestamp, or startDatetime is not earlier than endDatetime. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "unknown_point",
      -  "invalid_date_range",
      -  "invalid_query",
      -  "gdelt_rate_limited",
      -  "gdelt_unavailable"
      -]New value: +[
      +  "unknown_point",
      +  "offset_out_of_range",
      +  "invalid_date_range",
      +  "invalid_query",
      +  "gdelt_rate_limited",
      +  "gdelt_unavailable"
      +]
    • changedOutput schema / properties / expandedPoints / description
      Previous value: -"Timestep dates whose full article list is rendered in the text surface instead of the first 3, echoing the points input. Omitted when points was not supplied. Purely a rendering concern — structuredContent carries every article for every timestep either way."New value: +"Timestep dates this response is restricted to, each carrying its full article list — echoing the points input. Omitted when points was not supplied."
    • addedOutput schema / properties / nextOffset
      Added value: +{
      +  "description": "Offset of the next page, for the same inputs. Absent when this page reaches the last timestep.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when the query matched no coverage in the window — how to broaden the query or extend the window. Absent when timeline data was returned."New value: +"Guidance when the query matched no coverage in the window — how to broaden the query or extend the window — or, when this response is one page of several, which timesteps it returned out of how many. Absent when the whole timeline fit in one response."
    • changedOutput schema / properties / series / description
      Previous value: -"One or more time series (typically one for volume/tone, one per label for breakdowns)."New value: +"One or more time series (typically one for volume/tone), holding the timesteps of this page."
    • changedOutput schema / properties / series / items / properties / data / description
      Previous value: -"Time-ordered data points for this series."New value: +"Time-ordered data points of this series returned in this response."
    • changedOutput schema / properties / series / items / properties / data / items / properties / articles / description
      Previous value: -"Top articles driving coverage at this timestep. Present only in volume_with_articles mode."New value: +"Top articles driving coverage at this timestep — the first 3, or all of them for a timestep named in points. Present only in volume_with_articles mode."
    • addedOutput schema / properties / series / items / properties / data / items / properties / referenceCount
      Added value: +{
      +  "description": "How many articles GDELT returned for this timestep; articles carries the first 3 unless the timestep was named in points. Present whenever articles is.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / series / items / properties / peak
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "The point of the whole series with the largest absolute value, across every page — it may lie outside data. Omitted when the series has no points.",
      +  "properties": {
      +    "date": {
      +      "description": "Timestep of the peak, in ISO 8601 format.",
      +      "type": "string"
      +    },
      +    "value": {
      +      "description": "Value at the peak timestep.",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "date",
      +    "value"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / series / items / properties / pointCount
      Added value: +{
      +  "description": "Data points in the whole series, across every page — not only those in data. Present whenever the series has points.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / totalCount / description
      Previous value: -"Total number of data points across all series."New value: +"Total number of data points across all series of the full timeline, not this page."
  5. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"Search query using GDELT syntax. Same operators as gdelt_search_articles: phrases, boolean OR, sourcecountry:, sourcelang:, domain:, theme:, tone<."New value: +"Search query using GDELT syntax. Same operators as gdelt_search_articles: phrases, boolean OR, sourcecountry:, sourcelang:, domain:, theme: (GKG theme identifiers come from gdelt_search_themes), tone<."
  6. Changed5 schema fields changed
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "not": {
      -      "required": [
      -        "error"
      -      ]
      -    },
      -    "required": [
      -      "dateResolution",
      -      "series",
      -      "effectiveQuery",
      -      "mode",
      -      "totalCount"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "error"
      -    ]
      -  }
      -]New value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "series",
      +      "effectiveQuery",
      +      "mode",
      +      "totalCount"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • changedOutput schema / properties / dateResolution / description
      Previous value: -"Temporal resolution of the data points — 15min, hour, or day."New value: +"Temporal resolution of the data points — 15min, hour, or day — inferred from the spacing of the returned timesteps. Omitted when fewer than two distinct timesteps came back."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Only one of startDatetime / endDatetime was supplied, one of them is not a real UTC calendar timestamp, or startDatetime is not earlier than endDatetime. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `unknown_point`: A date passed in the points input matches no timestep in a non-empty timeline. `invalid_date_range`: Only one of startDatetime / endDatetime was supplied, one of them is not a real UTC calendar timestamp, or startDatetime is not earlier than endDatetime. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "no_timeline_data",
      -  "unknown_point",
      -  "invalid_date_range",
      -  "invalid_query",
      -  "gdelt_rate_limited",
      -  "gdelt_unavailable"
      -]New value: +[
      +  "unknown_point",
      +  "invalid_date_range",
      +  "invalid_query",
      +  "gdelt_rate_limited",
      +  "gdelt_unavailable"
      +]
    • changedOutput schema / properties / notice / description
      Previous value: -"Recovery hint when no timeline data was returned. Absent on successful responses."New value: +"Guidance when the query matched no coverage in the window — how to broaden the query or extend the window. Absent when timeline data was returned."
  7. Changed1 schema field changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Exactly one of startDatetime / endDatetime was supplied. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Only one of startDatetime / endDatetime was supplied, one of them is not a real UTC calendar timestamp, or startDatetime is not earlier than endDatetime. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."
  8. Changed1 schema field changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Exactly one of startDatetime / endDatetime was supplied. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request because its one-request-per-five-seconds limit was reached. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Exactly one of startDatetime / endDatetime was supplied. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request for its one-request-per-five-seconds limit, or too many requests were already queued for this one to start in time. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."
  9. Changed2 schema fields changed
    • changedOutput schema / properties / dateResolution / description
      Previous value: -"Temporal resolution of the data points — hour for short windows, day for longer."New value: +"Temporal resolution of the data points — 15min, hour, or day."
    • changedOutput schema / properties / dateResolution / enum
      Previous value: -[
      -  "hour",
      -  "day"
      -]New value: +[
      +  "15min",
      +  "hour",
      +  "day"
      +]
  10. Changed3 schema fields changed
    • changedInput schema / properties / timespan / description
      Previous value: -"Time window relative to now, e.g. \"24h\", \"7d\", \"1m\". Ignored when startDatetime/endDatetime are set. Maximum 3 months."New value: +"Time window relative to now, minimum \"15min\"; other examples: \"24h\", \"7d\", \"1m\". Ignored when startDatetime/endDatetime are set. Maximum 3 months."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Exactly one of startDatetime / endDatetime was supplied. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_unavailable`: GDELT DOC API is unreachable or rate-limited. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Exactly one of startDatetime / endDatetime was supplied. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_rate_limited`: GDELT rejected the request because its one-request-per-five-seconds limit was reached. `gdelt_unavailable`: GDELT DOC API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "no_timeline_data",
      -  "unknown_point",
      -  "invalid_date_range",
      -  "invalid_query",
      -  "gdelt_unavailable"
      -]New value: +[
      +  "no_timeline_data",
      +  "unknown_point",
      +  "invalid_date_range",
      +  "invalid_query",
      +  "gdelt_rate_limited",
      +  "gdelt_unavailable"
      +]
  11. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "dateResolution",
      +      "series",
      +      "effectiveQuery",
      +      "mode",
      +      "totalCount"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode. Declared by this tool: `no_timeline_data`: No timeline data returned for the query and time range. `unknown_point`: A date passed in the points input matches no timestep in this timeline. `invalid_date_range`: Exactly one of startDatetime / endDatetime was supplied. `invalid_query`: GDELT rejected the query string as malformed — bad keyword length, unbalanced parentheses, or an illegal character. `gdelt_unavailable`: GDELT DOC API is unreachable or rate-limited. Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "no_timeline_data",
      +            "unknown_point",
      +            "invalid_date_range",
      +            "invalid_query",
      +            "gdelt_unavailable"
      +          ],
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "dateResolution",
      -  "series",
      -  "effectiveQuery",
      -  "mode",
      -  "totalCount"
      -]
  12. Changed2 schema fields changed
    • addedInput schema / properties / points
      Added value: +{
      +  "description": "Timestep dates whose complete article list should be rendered in the text surface, e.g. [\"2024-01-05T12:00:00Z\"]. Take them verbatim from series[].data[].date in a prior response, or from the list an unknown_point error prints. Only affects volume_with_articles rendering — every timestep already carries its full article list in structuredContent regardless. Timesteps not named here show their first 3 links; a date matching no timestep is rejected rather than silently ignored.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / expandedPoints
      Added value: +{
      +  "description": "Timestep dates whose full article list is rendered in the text surface instead of the first 3, echoing the points input. Omitted when points was not supplied. Purely a rendering concern — structuredContent carries every article for every timestep either way.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  13. Changed4 schema fields changed
    • changedInput schema / properties / endDatetime / description
      Previous value: -"End datetime in GDELT format YYYYMMDDHHMMSS. Must pair with startDatetime."New value: +"End datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240131235959). Must pair with startDatetime; supplying only one of the two is rejected."
    • addedInput schema / properties / endDatetime / pattern
      Added value: +"^\\d{14}$"
    • changedInput schema / properties / startDatetime / description
      Previous value: -"Start datetime in GDELT format YYYYMMDDHHMMSS. Must pair with endDatetime."New value: +"Start datetime in GDELT format YYYYMMDDHHMMSS — exactly 14 digits, no separators (e.g. 20240101000000). Must pair with endDatetime; supplying only one of the two is rejected."
    • addedInput schema / properties / startDatetime / pattern
      Added value: +"^\\d{14}$"
  14. Changed2 schema fields changed
    • addedOutput schema / properties / endDatetime
      Added value: +{
      +  "description": "Echoed end datetime when provided (YYYYMMDDHHMMSS).",
      +  "type": "string"
      +}
    • addedOutput schema / properties / startDatetime
      Added value: +{
      +  "description": "Echoed start datetime when provided (YYYYMMDDHHMMSS).",
      +  "type": "string"
      +}
  15. Changed6 schema fields changed
    • addedOutput schema / properties / effectiveQuery
      Added value: +{
      +  "description": "Echoed query string for use in follow-up calls.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / mode / description
      Previous value: -"Timeline mode used."New value: +"Timeline mode used for this response."
    • changedOutput schema / properties / notice / description
      Previous value: -"Recovery hint when no data was returned. Absent on successful responses."New value: +"Recovery hint when no timeline data was returned. Absent on successful responses."
    • removedOutput schema / properties / query
      Removed value: -{
      -  "description": "Echoed query string.",
      -  "type": "string"
      -}
    • addedOutput schema / properties / totalCount
      Added value: +{
      +  "description": "Total number of data points across all series.",
      +  "type": "number"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "query",
      -  "mode",
      -  "dateResolution",
      -  "series"
      -]New value: +[
      +  "dateResolution",
      +  "series",
      +  "effectiveQuery",
      +  "mode",
      +  "totalCount"
      +]
  16. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly and openWorld; the description adds substantial operational detail beyond them: per-mode retention limits (3 months vs. presetable windows), pagination via nextOffset with 'otherwise identical inputs', the limit cap of 400, and the fact that each volume_with_articles timestep carries only its first 3 article links and a referenceCount capped at ten rather than all matches.

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 purpose and mode selection, and nearly every clause carries operative information. It is very dense, though — the article-truncation, pagination, and retention rules are compressed into two long sentences, which makes the response-shape details easy to skim past.

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 a 9-parameter tool with an output schema, the description covers what the schema cannot: what a page contains (limit timesteps, nextOffset), how per-timestep article data is truncated and how points restores it, and how retention differs by mode. An agent has everything needed to call it correctly, including the paging loop.

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 baseline is 3, and the description genuinely exceeds it by explaining cross-parameter interactions the schema documents only piecemeal: points returns complete article lists in volume_with_articles mode, smoothing 'needs N source steps' and can shift peaks later, and offset must be paired with identical inputs. Date-resolution inference ('15 minutes or hours for short windows, days for longer ones') is stated only here.

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?

Opens with a specific verb+resource: 'Retrieve a time series showing when news coverage of a topic spiked, or how average tone shifted over time.' It then enumerates each mode's distinct output, so an agent can tell this apart from gdelt_get_coverage_breakdown or gdelt_get_tone_distribution without opening schemas.

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?

Explicitly routes the agent between modes: 'volume' for normalized intensity, 'volume_raw' for distinct counts plus the norm denominator, 'volume_with_articles' named as 'the primary signal-detection mode' that avoids 'a follow-up gdelt_search_articles call', and 'tone' for sentiment. It also states a negative condition — that volume_raw and volume_with_articles cover only the last 3 months — which tells the agent when a mode is unusable.

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.