Game Stats AI

group_by_attribute

Read-only

Break a live count down by the values of one categorical attribute, most common first. source is Match, MatchPlayer, MatchEvent, Player, or Event; attribute_name must be an attribute at that level from list_attribute_types (for Event, also pass event_name_id). Only works on attributes with 50 or fewer unique values. Optional filters: version_id, occurred_after, occurred_before (ISO 8601), except on Player.

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": {
      "source": "<source>",
      "attribute_name": "<attribute_name>"
    },
    "name": "group_by_attribute"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of value rows to return (default 20, max 50).
`source`	Yes	What to count and break down.
`version_id`	No	Only include data from this game version.
`event_name_id`	No	Required when source is Event: the event name from list_event_names.
`attribute_name`	Yes	The attribute whose values to group by (from list_attribute_types at this level).
`occurred_after`	No	Only include data at or after this time (ISO 8601 date or date-time).
`occurred_before`	No	Only include data at or before this time (ISO 8601 date or date-time).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint, so the safety profile is covered; the description adds a hard cardinality ceiling (50 unique values) and default sort order, which are real behavioral facts. It does not describe the shape of a result row or what happens when the ceiling is exceeded (error vs. truncation). Useful additions, but not a full behavioral picture for an analytic query tool.

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?

A single dense paragraph with the core action front-loaded and constraints following in dependency order. Every clause carries information; the only mild density cost is packing source enum, prerequisites, cardinality limit, and filter caveats into one block without visual separation.

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 7-parameter aggregation tool with no output schema, the description covers what is required, what is conditional, what is disallowed, and the ordering of results. A short note on the returned row format (value plus count) would close the remaining gap, but an agent has enough to call this correctly.

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 coverage is 100%, so the baseline is 3, but the description genuinely adds cross-parameter semantics: event_name_id is conditional on source=Event, and the version/time filters are inapplicable when source=Player. Those conditional rules are not encoded in the schema and prevent misuse. Only 'limit' is left entirely to the schema.

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

Purpose4/5

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

States a specific operation (break a live count down by one categorical attribute's values, ordered most-common-first), which is concrete enough for an agent to know exactly what it produces. The 'live count' framing and the enumerated source levels sharpen the resource. It does not name how it differs from near-siblings like aggregate_attribute or attribute_histogram, so it stops short of 5.

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?

Provides strong preconditions: attribute_name must come from list_attribute_types at the given level, event_name_id is required for Event, and attributes must have 50 or fewer unique values. It also states filters are unavailable on Player, which is a genuine usage exclusion. What is missing is explicit routing guidance versus the sibling aggregate/histogram tools.

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

All Game Stats AI 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?