Game Stats AI

run_report

Read-only

Run one of this account's configured reports and return its rows. Reports are pre-aggregated: their time filter only supports the last 1, 7, or 30 days. Filters you omit fall back to the report's defaults (latest version, configured attribute filter defaults) EXCEPT threshold, which is never applied unless you pass it. The result echoes applied_filters (what actually ran) and total_row_count. A link to the report, pre-filtered to exactly what ran, is shown to the user automatically.

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": {
      "report_type": "<report_type>",
      "report_id": "<report_id>"
    },
    "name": "run_report"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of rows (and most recent time_series days) to return (default 50, max 100).
`filters`	No	Optional filter overrides. Known names: version_id (values are version ids from list_versions), occurred_after (one value: "1", "7" or "30" days), occurred_between (two ISO dates: from, to; event, retention, revenue, and session reports only), event_type_id (values from list_event_types), threshold (two values: min and max total sample count, e.g. ["40", ""] for min only; filters out low-sample rows), or a configured attribute filter name from the catalog with the values to keep.
`report_id`	Yes	The report's id from the report catalog.
`report_type`	Yes	The kind of report, as listed in the report catalog.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4/5.0

Behavior5/5

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

Well beyond the annotations, it discloses the pre-aggregation constraint (time filter limited to 1/7/30 days), the default-fallback rule for omitted filters, and the important exception that threshold is never applied unless passed. It also describes the response shape (applied_filters, total_row_count) and a user-visible side effect (an auto-shown link pre-filtered to what ran), which is exactly the kind of behavior an agent needs before invoking.

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?

Four dense sentences, front-loaded with what the tool does and followed by the constraints that could cause a wrong result; nothing is padding. The wording is somewhat compressed in places (the EXCEPT clause, the parenthetical default list) which costs a little readability.

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?

With no output schema, the description carries the return explanation and does so adequately (applied_filters, total_row_count, auto link). What is missing is the selection logic against the large family of typed report siblings and how the 13 report_type values relate to those separate tools.

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 adds real meaning: the threshold default-off rule and the fact that omitted filters fall back to configured defaults (latest version, attribute defaults) rather than being unset. One tension exists — the description says the time filter only supports 1/7/30 days while the schema permits occurred_between with two ISO dates for several report types — which slightly muddies the parameter guidance.

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 verb and resource ('Run one of this account's configured reports and return its rows') and notes the reports are pre-aggregated, which frames what kind of output to expect. It does not distinguish itself from the many typed siblings like get_event_report or get_retention_report, so an agent cannot tell from the description alone whether this generic runner supersedes them.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: it is for pulling rows from an already-configured report in the catalog. There is no explicit when-to-use versus the typed get_*_report tools or list_reports, and no stated prerequisites (e.g. that report_id must come from the catalog or list_versions).

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?