get_metadata_schema
List declared metadata fields with names, types, and descriptions to build metadata filters, sorts, aggregations, or groupings for document searches. Call when questions filter by typed attributes like year or status.
Instructions
List declared metadata fields (names, types, descriptions) so you can build metadata_filter / sort / aggregates / group_by for search_documents(mode="metadata"), or a metadata_filter that narrows mode="query". Call it only when the question filters by a typed attribute (year, status, category, …) or asks for counts / averages / extremes / distributions — not as a routine first step; ordinary discovery goes through browse_documents(). Call it WITHOUT folder_id first: one call returns the account-level fields plus every folder that declares its own, with folder ids — no need for get_folder_structure() beforehand. Pass a folder_id only to read one folder's effective schema (it falls back to the account-level one). Reuse the result for the rest of the conversation.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_metadata_schema"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| folder_id | No | Optional folder ID. Omit it for an overview: the account-level fields plus every folder that declares its own (on a folder-scoped connection, omission returns the scoped folder's schema instead). Pass "root" for the account-level schema only. Pass a folder ID for the fields that apply to its documents: fields are declared on a top-level folder and shared by every folder in it, and a top-level folder that declares none uses the account-level fields. |