Skip to main content
Glama
Sign In

Costory: Your Finops MCP

by io.costory.app-api
OverviewDiscussionsAdmin

list_dimension_candidates

Read-only

List native billing label keys that can be imported as label dimensions (not virtual dimensions). Use when the user asks which billing keys can be imported as label dimensions. Returns compact rows: key, ingested, imported, providers, numberValues, totalCostKeyPresent, proportionKeyPresent, costPercentageChange, topValues (top 8, Others omitted). Default drops keys already used in a published label (includeImported: true to keep them). Filter with query (substring on key / top values / providers), minCostPresent, sort (cost_desc default | cost_asc | coverage_desc | name_asc), limit (default 25, cap 50), offset. No suggestion engine — pick merges and value maps from topValues yourself. To add or change labels, call publish_label_dimensions once with an operations array (add / update / delete by id). The server merges them onto all existing label dimensions — do not resend the full list. Publishing takes about 10 minutes to show up in Explorer. Preview with dryRun: true (default), then call once with dryRun: false and confirm: true. Before rename or delete, call list_label_dimension_usages. EXAMPLE: "Which env-like billing keys are not dimensions yet?" → { query: "env" }

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": {
      "context": "<context>"
    },
    "name": "list_dimension_candidates"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoOrganization slug. Omit to auto-detect from your account (fails if you belong to multiple orgs).
sortNoSort order (default cost_desc).cost_desc
limitNoMax rows to return (default 25, cap 50).
queryNoSubstring filter on key, top values, or providers.
offsetNoNumber of rows to skip.
contextYesA 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 Do not quote the user or include names, emails, or other personal details.
llm_modelNoThe 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.
minCostPresentNoMinimum totalCostKeyPresent.
conversation_idNoThe 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.
includeImportedNoWhen false (default), drop keys already used in a published label.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • 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: -[
-  "context",
-  "llm_model"
-]New value: +[
+  "context"
+]
  2. Changed4 schema fields changed
    • 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"
+}
    • addedInput schema / required
      Added value: +[
+  "context",
+  "llm_model"
+]
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare it is a safe, closed-world read; the description goes far beyond that by disclosing the default filtering behavior (already-imported keys dropped unless includeImported), the exact return row shape and top-8 truncation, and the downstream constraint that publishing takes ~10 minutes to appear in Explorer with a dryRun-then-confirm sequence. It also warns there is no suggestion engine, so the agent must select merges and value maps itself.

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 it lists, when to use it) is front-loaded, and the trailing workflow guidance about publishing and dryRun is useful rather than padding. It is dense and fairly long, packing return format, filter semantics, and a multi-step downstream procedure into one block, which is slightly sprawling but each sentence carries operational value.

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?

With ten parameters and no output schema, the description correctly compensates by enumerating the returned fields, noting truncation of topValues, and spelling out default and cap behavior. It also covers the follow-on publish workflow and a worked example, leaving nothing an agent needs to call it correctly or chain it to the next tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter already carries its own description (sort enum, limit cap, query substring, includeImported default), so the description mostly restates the schema. The one genuine addition is the note that query matches key, top values, or providers and the instruction to derive merges and value maps from topValues, but that is modest value on top of a fully documented 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?

The description opens with a specific verb and resource ("List native billing label keys that can be imported as label dimensions") and explicitly excludes virtual dimensions, which is the nearest confusion risk given the sibling tools. An agent can distinguish this from list_label_dimensions and list_virtual_dimensions 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 states the trigger ("Use when the user asks which billing keys can be imported as label dimensions"), gives an inline example of how to call it, and routes to alternatives: publish_label_dimensions for add/update/delete, list_label_dimension_usages before rename/delete. When-not-to-use is implied by the reads-only framing and the explicit redirect for mutations.

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 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