List Google News headlines by section
google_news_headlines_listRetrieve Google News headlines grouped by section and edition, with publisher URLs. Use optional language and country inputs to target regional news coverage.
Instructions
List Google News headlines grouped by section for an edition, with publisher URLs. Optional inputs: language and country. Returns a list.
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": {
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "google_news_headlines_list"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| country | No | Two-letter country of the edition, e.g. `US`, `GB` or `JP`. Default: `US`. Send it with `language`; an unsupported pair is rejected with every supported pair listed. | |
| language | No | Language and locale of the edition, e.g. `en-US`, `de`, `pt-BR` or `zh-Hant`. Default: `en-US`. The 400 response for an unsupported pair lists every supported pair. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |