Find issues
find_issuesFind issues by what they are ABOUT, in plain words — by meaning as well as by words (where the server has its embedding model), so an issue that says the same thing differently or in another language is found, which search_issues (JQL) cannot do. The same search answers with pages (wiki pages) and files (PDF and Word files attached to an issue or a page, found by the words inside them): "everything on this counterparty" finds the contract and not only the issue that names it. Best first; match says what found each (words, meaning, or only near words — the weakest). unread_files lists the files this search could NOT read (a scan, a damaged or protected file, an old .doc): nothing found says nothing about those. Use search_issues for questions about fields (mine, overdue, in status X).
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": {
"text": "<text>"
},
"name": "find_issues"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | What it is about, in your own words. | |
| limit | No | How many of each kind to return (default 10, max 25). | |
| projectKey | No | Only this project (must be visible to the token). Omit for every project the token sees. |