Costory: Your Finops MCP

get_report_execution_widget

Read-only

Fetch an advanced view for one widget from get_report_execution. Use when the user asks for detail behind one widget of a report run. Pass widgetId and a view from its drillDown list. DIGEST tree returns the full formatted tree. Optional returnImage "link" or "base64" returns the PNG already stored on a GRAPH_SNAPSHOT (no re-render). Omit for the usual view. "base64" also attaches the PNG bytes — large, only if the host cannot fetch the URL. Other widget types have no stored image. Read-only; never starts new investigations. EXAMPLE: { executionId: "clx…", widgetId: "clx…", view: "series", returnImage: "link" }

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": {
      "executionId": "<executionId>",
      "widgetId": "<widgetId>",
      "view": "<view>",
      "context": "<context>"
    },
    "name": "get_report_execution_widget"
  }
}

Input Schema

Name	Required	Description
`slug`	No	Organization slug. Omit to auto-detect from your account (fails if you belong to multiple orgs).
`view`	Yes	`series`, `tree`, or `investigations`.
`context`	Yes	A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other personal details.
`widgetId`	Yes	Widget id within that execution.
`llm_model`	No	The model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Pass "unknown" if you are not certain. Recorded for the server developer's analytics.
`executionId`	Yes	Report execution id.
`returnImage`	No	Omit (default) for the usual view only. "link": same view plus imageUrl of the PNG already stored on a GRAPH_SNAPSHOT (no re-render). "base64": same plus an inline PNG block fetched from that URL — large payload, only if the host cannot fetch the URL. Widgets with no stored image keep the view and append JSON { "image": "unsupported", "message": "..." }.
`conversation_id`	No	The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 14, 2026

changedInput schema / properties / context / description

Previous value: -"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""New value: +"A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details."

changedInput schema / required

Previous value: -[
-  "executionId",
-  "widgetId",
-  "view",
-  "context",
-  "llm_model"
-]New value: +[
+  "executionId",
+  "widgetId",
+  "view",
+  "context"
+]

Changed4 schema fields changedNov 12, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "executionId",
-  "widgetId",
-  "view"
-]New value: +[
+  "executionId",
+  "widgetId",
+  "view",
+  "context",
+  "llm_model"
+]

Changed1 schema field changedOct 30, 2026

addedInput schema / properties / returnImage

Added value: +{
+  "description": "Omit (default) for the usual view only. \"link\": same view plus imageUrl of the PNG already stored on a GRAPH_SNAPSHOT (no re-render). \"base64\": same plus an inline PNG block fetched from that URL — large payload, only if the host cannot fetch the URL. Widgets with no stored image keep the view and append JSON { \"image\": \"unsupported\", \"message\": \"...\" }.",
+  "enum": [
+    "link",
+    "base64"
+  ],
+  "type": "string"
+}

First observedAug 19, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnlyHint and destructiveHint=false annotations, it discloses that the call never starts new investigations, that image returns serve an already-stored PNG with no re-render, that base64 payloads are large, and that unsupported widgets return a JSON marker instead of failing. The DIGEST tree return shape is also disclosed, which matters since there is no output schema.

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 most important information, what the tool does and the drillDown constraint, is front-loaded, and the example anchors the call shape. Some sentences duplicate schema-described enum behavior for returnImage, which is mild redundancy rather than waste.

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 8 parameters, 4 required, and no output schema, the description covers the inputs that matter and describes both the tree and image return paths. The analytics-only parameters (context, llm_model, conversation_id, slug) are fully documented in the schema and need no prose here.

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 schema baseline is 3, but the description adds a genuine constraint not encoded in the schema: the view must come from the widget's drillDown list. It also restates the returnImage tradeoffs, which the schema already covers, so the gain is real but partial.

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 names a specific verb and resource ("Fetch an advanced view for one widget from get_report_execution") and explicitly positions itself relative to its parent tool, saying it drills into one widget of a report run. An agent can distinguish it from get_report_execution and the dashboard/alert widget siblings without opening a schema.

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

Usage Guidelines5/5

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

It gives an explicit trigger ("Use when the user asks for detail behind one widget of a report run"), an explicit prerequisite (widgetId plus a view from the widget's drillDown list), and explicit when/when-not rules for returnImage: omit by default, use "link" normally, use "base64" only if the host cannot fetch the URL. It also rules out image requests for other widget types that have no stored image.

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

All Costory: Your Finops MCP 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?