Get AI Tell
get_ai_tellReturns one AI Tells Index entry by id. Returns the whole record: what the pattern is, why it reads as machine-written, before and after examples, the detection rule, severity and status with its history, false-positive notes, model attribution, platform notes, and sources with an evidence grade. Takes an Index id (kebab-case) or the ai_tell_id of a draft-lint hit. A lint registry pattern id (snake_case, such as pointing_emoji) also works: it opens the entry that pattern links to, and resolved_from names the pattern id. A tell is a probabilistic signal of low-effort writing, never proof of AI authorship; false_positive_notes says when human writing trips it. Public reference data. No user data is read and nothing is written.
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": {
"id": "<id>"
},
"name": "get_ai_tell"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The entry id, kebab-case, from the Index listing or a lint hit's ai_tell_id. A lint registry pattern id resolves to its linked entry. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| kind | Yes | ||
| tell | Yes | ||
| license | Yes | ||
| resolved_from | No | ||
| dataset_version | Yes |