Skip to main content
Glama

Trillboards DOOH Advertising

by io.github.snehdhruv
OverviewDiscussionsAdmin

get_dataset_stats

Get statistics about available causal training data: total tuples, unique creatives, venue diversity, date range.

Queries observation_stream for rows that have both a creative ID and a VAS outcome recorded, giving a picture of how much training data is available for the causal prediction engine.

WHEN TO USE:

  • Checking if enough data exists for reliable causal predictions

  • Understanding the diversity of training data (creatives, venues, time range)

  • Monitoring causal dataset health and growth

  • Planning data collection strategies

RETURNS:

  • data: Dataset statistics

    • total_tuples: number of context-action-outcome records

    • unique_creatives: number of distinct creatives with VAS data

    • unique_venue_types: number of distinct venue types represented

    • date_range: { start, end } of available data

    • observations_per_creative: { min, max, mean, median } distribution

  • metadata: { query_window_days }

  • suggested_next_queries: Follow-up queries

EXAMPLE: User: "How much causal training data do we have?" get_dataset_stats({})

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses that the tool queries observation_stream and filters for rows with both creative ID and VAS outcome, and it provides a detailed return structure. This goes beyond a simple 'get stats' statement, but it does not mention potential costs, staleness, or access requirements. Still, the provided behavioral context is substantial.

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

Conciseness4/5

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

The description is well-structured with clear sections (overview, when-to-use, returns, example). It is longer than strictly necessary for a zero-parameter tool, but every section adds value: the return spec is critical since no output schema is provided. The example is brief and illustrative.

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

Completeness5/5

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

Given zero parameters, no annotations, and no output schema, the description is highly complete. It specifies the data source, filtering criteria, all return fields with descriptions, usage contexts, and an example. This fully compensates for the absence of an output schema and leaves no ambiguity about the tool's behavior.

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?

The input schema has zero properties and the description confirms no arguments via the example 'get_dataset_stats({})'. With 0 params, baseline is 4; there is nothing more to explain. The description reinforces that the tool requires no parameters.

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 explicitly states 'Get statistics about available causal training data' and lists specific metrics (total tuples, unique creatives, venue diversity, date range). It also explains the internal query against observation_stream, distinguishing it from other get_* tools like get_analytics or get_network_stats. The focus on causal training data makes it unique among siblings.

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 provides clear conditions for using the tool (checking data sufficiency, diversity, health monitoring, planning). It does not explicitly mention alternatives or when-not-to-use scenarios, but the context is clear and directly tied to causal prediction needs. An explicit exclusion would push it to 5.

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 toolsInspect
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