Skip to main content
Glama

Get GDELT TV Breakdown

gdelt_get_tv_breakdown
Read-only

Rank TV stations or shows mentioning a query. Station values are percentages of each station’s monitored airtime, or raw matching 15-second clip counts with normalize=false. Show values always represent percentages of matching clips, even with normalize=false. Labels are preserved exactly; ellipsized show labels may not work as exact show: selectors. Returns 25 rows by default, up to 10,000 per page. Archive coverage varies by station; use gdelt_list_tv_stations for station IDs, network and market selectors, and monitoring date ranges.

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>",
      "breakdownBy": "<breakdownBy>"
    },
    "name": "gdelt_get_tv_breakdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum ranking rows per page (default 25, cap 10,000). Larger counts clamp with limitClamp; strict deployments reject them.
queryYesTV transcript query. Supports phrases, Boolean OR, station:CNN, network:CBS, market:"National", show:"Bloomberg Best", and context:"vaccine".
offsetNoZero-based row offset after descending-value and exact-label sorting. Use nextOffset with the same query inputs for the next page.
stationsNoStation IDs to select (e.g. ["CNN", "FOXNEWS"]) — the stationId values gdelt_list_tv_stations returns, not display labels such as "FOX News"; every supplied ID is forwarded. Alternatively select station:, network:, or quoted market: in query. A selector is required; obtain network and market values from gdelt_list_tv_stations.
timespanNoRelative window counting back from now (a number and unit such as d, m, or y). Now is past the end of most stations' monitoring, so for archived periods set startDatetime/endDatetime inside a station's range from gdelt_list_tv_stations. Ignored when startDatetime/endDatetime are set.
normalizeNoStation rankings: true returns station-airtime percentages; false returns matching 15-second clip counts. Show rankings always return matching-clip percentages.
breakdownByYesRank stations by their airtime share or matching clip count, or shows by percentage of matching clips.
endDatetimeNoUTC end in YYYYMMDDHHMMSS format. Must pair with an earlier startDatetime.
startDatetimeNoUTC start in YYYYMMDDHHMMSS format. Must pair with a later endDatetime.

Output Schema

NameRequiredDescriptionDefault
rowsNoRows sorted by descending value, breaking ties by exact label, from the requested page.
errorNoPresent when the call failed. Absent on success.
limitNoApplied maximum rows on this page.
noticeNoWhen no rows matched: the resolved timespan window; for each selected station whose monitoring range the window misses, that range and how to search inside it; and how to check station monitoring ranges. On show rankings, that values are percentages of matching clips and ellipsized labels may not work as show: selectors. On station rankings whose page has rows without a station ID, why: the station catalog did not load, or has no entry for the named labels. Absent on a non-empty station ranking whose rows on the page all carry station IDs.
offsetNoZero-based offset of this ranking page.
totalRowsNoFull ranking row count before pagination.
truncatedNoTrue when additional rows remain after this page.
valueUnitNoStation-airtime percentage, matching-clip percentage for shows, or raw matching 15-second clip count for stations.
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; absent when no rows remain.
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.
effectiveQueryNoEchoed query for follow-up calls.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / stations / description
      Previous value: -"Station IDs to select; every supplied ID is forwarded. Alternatively select station:, network:, or quoted market: in query. A selector is required; obtain values from gdelt_list_tv_stations."New value: +"Station IDs to select (e.g. [\"CNN\", \"FOXNEWS\"]) — the stationId values gdelt_list_tv_stations returns, not display labels such as \"FOX News\"; every supplied ID is forwarded. Alternatively select station:, network:, or quoted market: in query. A selector is required; obtain network and market values from gdelt_list_tv_stations."
    • changedInput schema / properties / timespan / description
      Previous value: -"Relative time window, such as 1m or 6m. Ignored when both explicit datetimes are supplied. Check per-station archive coverage before selecting a window."New value: +"Relative window counting back from now (a number and unit such as d, m, or y). Now is past the end of most stations' monitoring, so for archived periods set startDatetime/endDatetime inside a station's range from gdelt_list_tv_stations. Ignored when startDatetime/endDatetime are set."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: Only one explicit datetime was supplied, a datetime is not a real UTC timestamp, or startDatetime is not earlier than endDatetime. `offset_out_of_range`: The requested row offset is at or beyond the end of a non-empty ranking. `invalid_query`: GDELT rejected the query or the TV timespan is malformed. `gdelt_rate_limited`: GDELT rejected its request-spacing limit, or the request queue could not start this call in time. `gdelt_unavailable`: GDELT TV 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: `invalid_date_range`: Only one explicit datetime was supplied, a datetime is not a real UTC timestamp, or startDatetime is not earlier than endDatetime. `offset_out_of_range`: The requested row offset is at or beyond the end of a non-empty ranking. `invalid_query`: A stations entry is not a station ID, GDELT rejected the query, or the TV timespan is malformed. `gdelt_rate_limited`: GDELT rejected its request-spacing limit, or the request queue could not start this call in time. `gdelt_unavailable`: GDELT TV API is unreachable or temporarily returned no usable data. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / notice / description
      Previous value: -"Empty-result guidance, show percentage and selector limitations, or station catalog resolution limitations."New value: +"When no rows matched: the resolved timespan window; for each selected station whose monitoring range the window misses, that range and how to search inside it; and how to check station monitoring ranges. On show rankings, that values are percentages of matching clips and ellipsized labels may not work as show: selectors. On station rankings whose page has rows without a station ID, why: the station catalog did not load, or has no entry for the named labels. Absent on a non-empty station ranking whose rows on the page all carry station IDs."
  2. Changed1 schema field changed
    • 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. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses non-obvious behavior: station values are airtime percentages unless normalize=false, show values are always matching-clip percentages even with normalize=false, labels are preserved exactly and ellipsized show labels may break exact show: selectors, and larger limits clamp with limitClamp or are rejected in strict deployments. The archive-coverage caveat also prevents an agent from assuming uniform monitoring windows.

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 most decision-relevant information—what is ranked and the percentage/count distinction—is front-loaded, and pagination and coverage caveats come last. A few statements duplicate the schema (normalize semantics, default 25 rows), costing some density, but no sentence is filler.

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 ranking tool with an output schema, the description covers everything an agent needs before calling: how to select stations, how percentages differ by breakdown, pagination via nextOffset, clamping risk, and the archive-coverage limitation. Return-value shape is correctly left to the output schema rather than restated.

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 baseline is 3, but the description adds meaning the schema does not: the warning that ellipsized show labels may not work as exact show: selectors, and the interaction where normalize behaves differently for show vs. station breakdowns. It largely mirrors the schema's own normalize, timespan, and limit text, which keeps it from a 5.

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 opens with a specific verb+resource: 'Rank TV stations or shows mentioning a query', and the breakdownBy semantics (station airtime share / matching clip count vs. show matching-clip percentage) make the two output modes explicit. This separates it from sibling retrieval tools like gdelt_search_tv or gdelt_get_tv_clips, which return clips rather than rankings.

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

Usage Guidelines4/5

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

It gives concrete routing guidance: use gdelt_list_tv_stations for station IDs, network and market selectors, and monitoring date ranges, and it states a selector is required. It also warns that timespan is inappropriate for archived periods and to set startDatetime/endDatetime inside a station's range instead. It stops short of explicitly contrasting when to choose this over gdelt_get_coverage_breakdown or gdelt_get_tone_distribution.

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.