Trillboards DOOH Advertising

export_dataset

Export observation data as a structured dataset. Supports filtering by time, geography, venue type, and observation family.

Queries the relevant table based on the selected dataset type, applies filters, and returns every matching row as structured data, a page at a time: up to 10,000 observation rows or 1,000 cross-signal insights per call, newest first. When more rows match, metadata.truncated is true and metadata.next_cursor reads the next page: call again with the same dataset and filters and cursor set to it, until truncated is false.

WHEN TO USE:

Exporting audience data for external analysis
Building datasets for machine learning or reporting
Getting structured vehicle or commerce data for a specific time/place
Creating cross-signal datasets for correlation analysis

RETURNS:

data: Array of dataset rows (schema varies by dataset type)
metadata: { row_count, export_id, dataset, filters_applied, time_range, truncated, next_cursor }
suggested_next_queries: Related exports or analyses

Dataset types:

observations: Raw observation stream data (all families)
audience: Audience-specific data (face_count, demographics, attention, emotion)
vehicle: Vehicle counting and classification data
cross_signal: Pre-computed cross-signal correlation insights

EXAMPLE: User: "Export audience data from retail venues last week" export_dataset({ dataset: "audience", filters: { time_range: { start: "2026-03-09", end: "2026-03-16" }, venue_type: ["retail"] }, format: "json" })

User: "Get vehicle data near geohash 9q8yy" export_dataset({ dataset: "vehicle", filters: { time_range: { start: "2026-03-15", end: "2026-03-16" }, geo: "9q8yy" } })

Input Schema

TableJSON Schema

Name	Required	Description
`cursor`	No	The previous page's metadata.next_cursor, to read the next page (same dataset and filters).
`format`	No	Export format (default: json). Currently only JSON is supported.
`dataset`	Yes	Type of dataset to export
`filters`	Yes	Filters to apply to the export

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 25, 2026

addedInput schema / properties / cursor

Added value: +{
+  "description": "The previous page's metadata.next_cursor, to read the next page (same dataset and filters).",
+  "maxLength": 2000,
+  "type": "string"
+}

Changed9 schema fields changedAug 7, 2026
- addedInput schema / properties / dataset / description
```
Added value: +"Type of dataset to export"
```
- addedInput schema / properties / filters / description
```
Added value: +"Filters to apply to the export"
```
- addedInput schema / properties / filters / properties / geo / description
```
Added value: +"Filter by geohash-6 prefix"
```
- addedInput schema / properties / filters / properties / observation_family / description
```
Added value: +"Filter by observation families (for observations dataset)"
```
- addedInput schema / properties / filters / properties / time_range / description
```
Added value: +"Time range filter (required for observations/audience/vehicle)"
```
- addedInput schema / properties / filters / properties / time_range / properties / end / description
```
Added value: +"End date/time (ISO 8601 or YYYY-MM-DD)"
```
- addedInput schema / properties / filters / properties / time_range / properties / start / description
```
Added value: +"Start date/time (ISO 8601 or YYYY-MM-DD)"
```
- addedInput schema / properties / filters / properties / venue_type / description
```
Added value: +"Filter by venue types"
```
- addedInput schema / properties / format / description
```
Added value: +"Export format (default: json). Currently only JSON is supported."
```
AddedMar 17, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains pagination behavior, row limits, ordering (newest first), and the next_cursor mechanism for fetching additional pages. It also clarifies that results are returned directly as structured rows, not as a separate file artifact, which is highly useful for an agent deciding how to invoke and consume results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Although long, the description is well-organized with clear sections: overview, pagination, when to use, returns, dataset types, and examples. Every section earns its place, especially given the tool's pagination and dataset variety. The opening sentence is front-loaded and the examples make the structure easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with no output schema, the description compensates well by documenting the return shape and pagination contract. It explains dataset types and provides usage examples. It does not explicitly call out that time_range is required for observations/audience/vehicle, though the schema already states this; this minor omission is acceptable because the schema covers it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful value beyond the schema by elaborating on each dataset type (e.g., audience includes face_count, demographics, attention, emotion) and by providing two realistic examples that map user intent to exact parameter values. It does not fully detail all filter constraints, but the schema already covers those, so no critical gap exists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Export observation data as a structured dataset' and enumerates the filter dimensions. It clearly distinguishes itself from siblings like export_cohort or get_analytics by specifying export semantics and supported dataset types. An agent can understand exactly what this tool does and when to prefer it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

A dedicated 'WHEN TO USE' section lists concrete scenarios: exporting for external analysis, building ML/reporting datasets, getting structured vehicle or commerce data, and creating cross-signal datasets. It gives a clear context for use, but it does not explicitly name alternatives or describe when NOT to use this tool, such as for interactive exploration or simple lookups.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Trillboards DOOH Advertising tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?