Search Wikipedia
wikipedia_search_listSearch a Wikipedia edition by query and filters to retrieve paginated results with snippets, match ranges, totals, and suggestions.
Instructions
Search a Wikipedia edition, with snippets, match ranges, totals and suggestions. Requires query. Returns a list (use cursor when paginated).
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>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "wikipedia_search_list"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Wikimedia edition code, e.g. `en`, `de`, `ja`, `simple` or `zh-min-nan`. Default: `en`. | en |
| sort | No | Result order: relevance (default), create_timestamp, incoming_links, last_edit, title_natural, just_match, none or random, optionally with `_asc` or `_desc`. | |
| limit | No | Results per page, 1 to 500. Default: 50. | |
| query | Yes | Required. Search text. Operators such as `insource:`, `incategory:` and `intitle:` work. A plain `insource:/.../` regular expression can be slow; prefer words or `insource:"..."`. At most 300 characters. | |
| cursor | No | Cursor from `page.nextCursor` of the previous response. It only works with the same filters. Rankings can shift between pages, so a title can repeat at a page boundary; de-duplicate by `pageId`. | |
| offset | No | First result to return, 0 to 9999. Use `cursor` to continue a walk. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| 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. | |
| namespace | No | Namespace id, e.g. `0` for articles or `14` for categories. | |
| 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. |