query_layer
Filter, select, group and sum any layer's data by column values to answer questions like airports in Karnataka or block areas rolled up to district totals. Check the schema first for column names.
Instructions
Query a layer's data with filters and grouping. Reads the parquet file at runtime. Supports: select specific columns, filter by column values, group by a column to get counts, and sum numeric columns per group (e.g. roll block areas up to district totals). Use get_layer_schema first to discover column names. Examples: 'airports in Karnataka' -> where: {state: 'KA'}, 'forest types' -> group_by: 'type', 'health facilities in Bihar' -> where: {state: 'BIHAR'}, select: ['name', 'type'].
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": {
"layer_id": "<layer_id>"
},
"name": "query_layer"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sum | No | Numeric columns to total per group (requires group_by). Adds {sums: {group: {col: total}}}. Use this to roll finer units up, e.g. block-level areas to district totals. Shares/percentages are not additive: sum the area columns and recompute shares. | |
| limit | No | Max rows (default 100, max 1000) | |
| where | No | Filter conditions as {column: value} pairs. Exact, case-insensitive match on flat columns (not partial). Values may contain commas. | |
| select | No | Column names to return. Omit for all non-geometry columns. | |
| group_by | No | Column to group by. Returns {value: count} instead of rows. | |
| layer_id | Yes | Layer ID to query | |
| include_centroid | No | Include _lat/_lng centroid coordinates (defaults to true). Set false to exclude. |