Game Stats AI

add_dashboard_card

Add a card to the end of the account's home dashboard. Confirm the card with the user before calling this: everyone on the account sees it. Sources: built_in needs key; event_metric needs event_name_id and aggregation (plus attribute_name for sum and average); report needs report_id from list_reports and metric (a metric label from list_reports), and event_type_id for character reports.

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>"
    },
    "name": "add_dashboard_card"
  }
}

Input Schema

Name	Required	Description
`key`	No	built_in only: the built-in metric.
`label`	No	Optional custom card title.
`metric`	No	report only: the metric label as listed in the report catalog.
`source`	Yes	Where the card's number comes from.
`display`	No	number (one value with its change and a chart) or top_list (top 5). Defaults to number.
`filters`	No	report only: narrow the card to some of the report's filter values.
`report_id`	No	report only: a report id from the report catalog.
`aggregation`	No	event_metric only.
`granularity`	No	How the number card charts the range. Defaults to auto.
`event_name_id`	No	event_metric only: id from list_event_names.
`event_type_id`	No	report only, character reports: id from list_event_types.
`attribute_name`	No	event_metric only: the numeric event attribute for sum and average.
`breakdown_attribute`	No	event_metric only: the attribute a top_list card ranks by.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 8, 2026

changedInput schema / properties / display / description

Previous value: -"number (one value with its change), time_series (a chart), or top_list (top 5). Defaults to number."New value: +"number (one value with its change and a chart) or top_list (top 5). Defaults to number."

changedInput schema / properties / display / enum

Previous value: -[
-  "number",
-  "time_series",
-  "top_list"
-]New value: +[
+  "number",
+  "top_list"
+]

changedInput schema / properties / granularity / description

Previous value: -"time_series only. Defaults to auto."New value: +"How the number card charts the range. Defaults to auto."

First observedNov 8, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, but say nothing about blast radius. The description adds real context beyond them: the card is appended to the account-wide home dashboard and is visible to everyone on the account, which is why user confirmation is required. It stops short of covering duplicate handling or what the response contains.

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?

Front-loads the action and the safety-critical confirmation instruction before the conditional detail. The trailing source-rules sentence is dense but every clause carries required information; no filler.

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 13-parameter write tool with no output schema, the description covers the branching logic that determines which parameters are mandatory, which is the highest-risk part. It omits mention of optional display, granularity, label, filters, and breakdown_attribute, but those are fully documented in the schema.

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?

With 100% schema coverage the baseline is 3, but the description adds composed conditional rules the per-field schema text does not: built_in requires key, event_metric requires event_name_id plus aggregation (and attribute_name for sum/average), report requires report_id plus metric and event_type_id for character reports. This is genuine cross-parameter meaning, though display/granularity/filters/breakdown_attribute are left to the schema.

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?

States a specific verb and resource plus placement: 'Add a card to the end of the account's home dashboard.' No sibling tool does this, and the description makes the mutation target and effect immediately clear.

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?

Gives a concrete precondition ('Confirm the card with the user before calling this') and routes the agent to dependency tools (list_reports for report_id/metric, list_event_names, list_event_types). It lacks explicit when-not guidance or a named alternative, but for a create-only tool the routing guidance is strong.

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?