identify_project
Identify the most relevant project from a text snippet by scoring it against your project corpus. Use this to route queries to the correct project context before responding.
Instructions
Score a text snippet against the indexed project corpus and return the best-match project.
Returns the top project ID, a confidence score (0.0-1.0), and the next two runners-up.
USE WHEN: the user pastes a question or note and you need to route it to the right project's context before answering. NOT FOR: detecting the user's CURRENT project — use get_active_project, which factors in CWD and window title.
BEHAVIOR: pure read; runs TF-IDF + project-keyword scoring. No side effects.
PARAMETERS: text: snippet to classify. Required, non-empty. Longer text scores more reliably; aim for 50+ characters.
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": "identify_project"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |