Skip to main content
Glama

Get cost reconciliation

get_cost_reconciliation
Read-only

Read what each cloud credential's provider billed for a month against Ankra's estimate for the same clusters - the document GET /org/cloud-cost/reconciliation serves. month is a UTC calendar month as YYYY-MM, not in the future (the last closed month when omitted; for the running month both sides are month to date). Per credential: state (absent when no billing document was imported: unknown, not zero), the imports with each attempt's reason, and in the invoice's own currency and minor units invoice_minor (tax_minor and credit_minor set apart), matched_minor placed on clusters and unmatched_minor not, estimate_minor for those clusters converted at estimate_fx, and difference_pct, stated over difference_coverage (the clusters measured for the hours they existed, with their share of the invoice and of the hours: read it as the whole invoice's accuracy only when both shares are 100), null with difference_reason saying why when it cannot be stated. difference_caveat says what a difference over part of the invoice leaves out and names billed lines in priced categories placed on no cluster. null is unknown, never zero or agreement. Requires billing.read. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_cost_reconciliation"
  }
}

Input Schema

NameRequiredDescriptionDefault
monthNoUTC calendar month as YYYY-MM, not in the future. Omit for the last closed month.
project_idNoUUID of a project to reconcile, or all for the whole organisation. Leave it out to read the project the conversation or token is in. Read for one project, only credentials whose invoice places a line on one of its clusters are listed, with invoice_withheld true: the invoice-wide totals and unplaced lines are left out because an invoice spans other projects, and matched_minor and difference_pct are that project's clusters alone.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / project_id / description
      Previous value: -"UUID of a project to reconcile, or all for the whole organisation. Leave it out to read the project the conversation or token is in. Only the billed clusters narrow: a credential's documents and invoice totals are the organisation's, because an invoice is."New value: +"UUID of a project to reconcile, or all for the whole organisation. Leave it out to read the project the conversation or token is in. Read for one project, only credentials whose invoice places a line on one of its clusters are listed, with invoice_withheld true: the invoice-wide totals and unplaced lines are left out because an invoice spans other projects, and matched_minor and difference_pct are that project's clusters alone."
  2. Changed1 schema field changed
    • addedInput schema / properties / project_id
      Added value: +{
      +  "description": "UUID of a project to reconcile, or all for the whole organisation. Leave it out to read the project the conversation or token is in. Only the billed clusters narrow: a credential's documents and invoice totals are the organisation's, because an invoice is.",
      +  "type": "string"
      +}
  3. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only say readOnlyHint=true, and the description goes far beyond that: it declares the billing.read permission, states that null/absent state means unknown rather than zero, and explains that difference_pct is only the whole invoice's accuracy when difference_coverage shares are 100. That is exactly the kind of semantic guardrail an agent cannot get from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the body is a single sprawling sentence chain with nested em-dash clauses that is hard to scan. Given there is no output schema the return-value detail has to live somewhere, but the packing is denser than necessary.

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-shape burden and does so thoroughly: per-credential state, imports and attempt reasons, minor-unit amounts, matched/unmatched, estimate_fx, difference_pct with coverage and caveat. It stops short of telling the agent how this reconciles against the other cost/savings tools, which is the main remaining gap.

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; the description still earns an increment by adding that for the running month both sides are month-to-date, which the schema does not say. For project_id it mostly restates the already-detailed schema text rather than adding new meaning.

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?

The opening sentence gives a specific verb and resource: read what each cloud credential's provider billed for a month against Ankra's estimate for the same clusters, and names the backing endpoint. That is materially more precise than the cost siblings (get_cluster_cost, get_fleet_cloud_cost, get_stack_cost), though it never explicitly routes between 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 by content: use it to compare invoiced spend against estimates. The description does state prerequisites ('Requires billing.read') and defaults (month omitted means last closed month), but gives no explicit when-to-use/when-not guidance relative to the other cost tools in the fleet.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.