Use this when the user wants a high-level overview or dashboard of their entire cloud infrastructure. Returns cost by cloud provider, top services per cloud, top projects per cloud, recent cost anomalies, and recent cloud incidents — all in a single call. Do NOT use this for detailed drill-downs (use run_query), single-provider analysis, or anomaly-only queries.

Use this when the user wants to check for active cloud platform outages, service disruptions, or incidents from AWS, Google Cloud, or Azure. Do NOT use this for cost anomalies (use get_anomalies) or support tickets (use list_tickets).

Use this when the user wants to view details of a specific cloud platform incident. Accepts either the incident ID or a partial title match (case-insensitive). Do NOT use this for listing all incidents (use get_cloud_incidents) or anomalies (use get_anomalies).

Use this when the user wants to check for unexpected cost spikes, billing anomalies, or unusual spending patterns. Returns recent anomalies with severity and impact. Do NOT use this for optimization recommendations or savings opportunities (use list_optimization_recommendations), regular cost analysis (use run_query), or viewing alerts (use list_alerts).

Use this when the user wants to view details of a specific cost anomaly by its ID. Returns full anomaly data including affected resources and cost impact. Do NOT use this for listing all anomalies (use get_anomalies).

Use this when the user wants to see their saved Cloud Analytics reports or browse available reports. Returns a paginated list of reports with their IDs and metadata. Do NOT use this for running queries (use run_query) or getting report results (use get_report_results).

Use this when the user wants to analyze cloud costs, generate a cost breakdown, view spending trends, or run a custom analytics query across their cloud providers. Accepts a structured config with data source, metrics, dimensions, time range, and filters. Do NOT use this for listing saved reports (use list_reports), checking anomalies (use get_anomalies), or viewing budgets (use list_budgets). Fields that are not populated will use their default values if needed. To limit the number of rows returned per group, set the limit.value field inside each config.group[] entry (maximum 25). If possible, use timeRange instead of customTimeRange when no specific dates are given. Use "includeCurrent": true to include the current in-progress month. Use "includeCurrent": false only when asking about a fully completed past period. Always use "metrics" (array) not the deprecated "metric" (object).

ALWAYS include a "group" with id "service_description" and type "fixed" unless the user explicitly asks to group by something else. This gives a per-service cost breakdown which is always the most useful default.

Common grouping dimension IDs (all type "fixed"):
  "service_description" — cloud service (default)
  "project_id"          — GCP project / AWS account / Azure subscription (use when user asks to group by project, account, or subscription)
  "cloud_provider"      — cloud provider (AWS / GCP / Azure)

IMPORTANT — filter values are dimension IDs, never display names. Before filtering on any dimension
you are unsure about, call get_dimension({type, id}) to retrieve the exact valid values for this customer.
Known cloud provider IDs (cloud_provider, type "fixed"):
  "amazon-web-services" = AWS, "google-cloud" = GCP, "microsoft-azure" = Azure

Example — top AWS services last month:
{
  "config": {
    "dataSource": "billing",
    "metrics": [{"type": "basic", "value": "cost"}],
    "timeRange": {"mode": "last", "amount": 1, "unit": "month", "includeCurrent": true},
    "filters": [{"id": "cloud_provider", "type": "fixed", "values": ["amazon-web-services"]}],
    "group": [{"id": "service_description", "type": "fixed", "limit": {"metric": {"type": "basic", "value": "cost"}, "sort": "desc", "value": 10}}]
  }
}

Use this when the user wants a simple cost breakdown by service, project, or cloud provider (e.g. 'What are my top services by cost?', 'Which projects cost the most?'). Returns the top-N items ranked by cost descending. For complex multi-filter or multi-metric queries, use run_query instead.

Use this when the user wants to see monthly spend over time (e.g. 'Show me my cost trend', 'How has my spend changed over the last 6 months?'). Returns monthly cost data points, optionally broken down by service/project/cloud. For daily granularity or custom time intervals, use run_query instead.

Use this when the user wants to compare spend between two time periods (e.g. 'Compare my costs this quarter vs last quarter', 'How did January compare to February?'). Period 1 is a rolling lookback; period 2 is an explicit date range. For more than two periods or advanced comparative analysis, use run_query instead.

Use this when the user asks about optimization, recommendations, insights, savings opportunities, rightsizing, idle resources, security findings, or cost reduction suggestions. Also use this when the user asks 'what insights are available?' or 'show me insights'. This is the primary tool for 'what can I optimize?', 'how can I save money?', and 'what insights do I have?' questions. Returns a prioritized list of actionable insights with estimated daily savings. Do NOT use this for cost anomalies/spikes (use get_anomalies) or budget tracking (use list_budgets).

Use this when the user wants to see which specific resources are affected by an optimization insight. Returns resource IDs, accounts, potential savings, and remediation details. Do NOT use this for listing all insights (use list_insights).

Use this when the user wants to retrieve the data results of a specific saved report. Accepts either the report ID or a partial name (case-insensitive). Do NOT use this for listing all reports (use list_reports) or running ad-hoc queries (use run_query).

Get the configuration of a specific Cloud Analytics report by ID. Returns the stored report object including name, type, and a nested 'config' field containing data source, metrics, dimensions, time range, filters, and visualization settings.

Use this when the user wants to save a new Cloud Analytics report with a specific configuration. Ask the user to confirm the report parameters before executing. Do NOT use this for one-time queries without saving (use run_query).

Use this when the user wants to modify an existing saved Cloud Analytics report. Supports partial updates. Ask the user to confirm changes before executing. Do NOT use this for running ad-hoc queries (use run_query).

Use this ONLY when the user explicitly asks to verify their account connection or check who they are logged in as. Do NOT call this proactively before other tool calls — the OAuth token already guarantees the user is authenticated. Do NOT use this for listing users in the organization (use list_users).

Use this when the user wants to see available dimensions for cost analysis queries. Returns a list of dimension types and values that can be used with run_query. Do NOT use this for running cost queries directly (use run_query) or viewing allocations (use list_allocations).

Use this to look up the valid filter values for a specific dimension before calling run_query — for example, call get_dimension({type: 'fixed', id: 'cloud_provider'}) to get the exact provider IDs available for this customer. Also use this when the user wants to view dimension details. Do NOT use this for listing all dimensions (use list_dimensions) or running queries (use run_query).

Use this when the user wants to view their support tickets, check ticket status, or review open issues. Returns tickets with status, priority, and platform. Supports partial subject filtering. Do NOT use this for cloud incidents (use get_cloud_incidents) or cost alerts (use list_alerts).

Returns details of a specific support ticket from the DoiT API by its ID.

Returns all comments on a support ticket. For customers, only public comments are returned. For DoiT employees, both public and private comments are returned.

Adds a comment to an existing support ticket. For customers, comments are always public. For DoiT employees, comments can be marked as private (internal notes) by setting the private field to true.

Use this when the user wants to create a new support ticket. Ask the user to confirm the ticket details before executing. Do NOT use this for viewing existing tickets (use list_tickets) or cloud incidents (use get_cloud_incidents).

Use this when the user wants to see their invoices, check billing history, or review payment records. Returns a list of invoices with amounts, dates, and status. Do NOT use this for cost analysis (use run_query) or budget tracking (use list_budgets).

Use this when the user wants to view details of a specific invoice by its ID. Returns full invoice data including line items and status. Do NOT use this for listing all invoices (use list_invoices) or cost analysis (use run_query).

Use this when the user wants to see their cost allocation rules or configurations. Returns a list of allocations. Supports partial name filtering. Do NOT use this for cost queries (use run_query) or labels (use list_labels).

Use this when the user wants to view details of a specific cost allocation. Accepts either the allocation ID or a partial name (case-insensitive). Do NOT use this for listing all allocations (use list_allocations) or running queries (use run_query).

Use this when the user wants to create a new cost allocation rule. Ask the user to confirm the allocation parameters before executing. Do NOT use this for viewing existing allocations (use list_allocations) or labels (use create_label).

Use this when the user wants to modify an existing cost allocation. Ask the user to confirm changes before executing. Do NOT use this for creating new allocations (use create_allocation) or viewing allocations (use list_allocations).

Use this when the user wants to browse their cloud assets, subscriptions, or resources. Returns a paginated list of assets. Supports partial name filtering. Do NOT use this for cost analysis (use run_query) or checking invoices (use list_invoices).

Use this when the user wants to view details of a specific cloud asset. Accepts either the asset ID or a partial name (case-insensitive). Do NOT use this for listing all assets (use list_assets) or cost analysis (use run_query).

Use this when the user wants to see their cost alerts or check alert configurations. Returns a paginated list of alerts. Do NOT use this for anomaly detection (use get_anomalies) or budget tracking (use list_budgets).

Use this when the user wants to view the details of a specific cost alert. Accepts either the alert ID or a partial name (case-insensitive). Do NOT use this for listing all alerts (use list_alerts) or anomalies (use get_anomalies).

Use this when the user wants to set up a new cost alert with thresholds and notification settings. Ask the user to confirm the alert parameters before executing. Do NOT use this for creating budgets (use create_budget) or viewing existing alerts (use list_alerts).

Use this when the user wants to modify an existing cost alert. Supports partial updates. Ask the user to confirm changes before executing. Do NOT use this for creating new alerts (use create_alert) or budgets (use create_budget).

Use this when the user wants to trigger an automated CloudFlow workflow by its flow ID. This executes automation that may modify cloud resources externally. Ask the user to confirm the flow ID and any parameters before executing. Do NOT use this for viewing CloudFlow definitions or checking available flows.

Use this when the user wants to see the organizations in their DoiT account. Returns a list of organizations. Do NOT use this for listing users (use list_users) or platforms (use list_platforms).

Use this when the user wants to see available cloud platforms in their DoiT account. Returns a list of platforms. Do NOT use this for cloud incidents (use get_cloud_incidents) or products (use list_products).

Use this when the user wants to see users in their DoiT organization or check who has access. Returns a list of users with roles. Do NOT use this for listing roles (use list_roles) or validating the current user (use validate_user).

Use this when the user wants to update a user's information such as name, job function, phone, language, or role. Ask the user to confirm the changes before executing. Do NOT use this for inviting new users (use invite_user) or listing users (use list_users).

Use this when the user wants to invite a new person to the organization. Ask the user to confirm the email, role, and organization before executing. Do NOT use this for updating existing users (use update_user) or listing users (use list_users).

Use this when the user wants to see available roles in their DoiT organization. Returns a list of roles with permissions. Do NOT use this for listing users (use list_users) or organizations (use list_organizations).

Use this when the user wants to see available DoiT products or services. Returns a list of products. Do NOT use this for cloud incidents (use get_cloud_incidents) or platforms (use list_platforms).

Use this when the user wants to see their resource labels or label configurations. Returns a list of labels with their metadata. Do NOT use this for annotations (use list_annotations) or label assignments (use get_label_assignments).

Use this when the user wants to view details of a specific label. Accepts either the label ID or a partial name (case-insensitive). Do NOT use this for listing all labels (use list_labels) or annotations (use list_annotations).

Use this when the user wants to create a new resource label. Ask the user to confirm the label details before executing. Do NOT use this for viewing existing labels (use list_labels) or annotations (use create_annotation).

Use this when the user wants to modify an existing label. Supports partial updates. Ask the user to confirm changes before executing. Do NOT use this for creating new labels (use create_label) or annotations (use update_annotation).

Use this when the user wants to see which resources are assigned to a specific label. Returns a list of assigned objects. Do NOT use this for viewing label details (use get_label) or allocations (use list_allocations).

Use this when the user wants to assign or unassign cloud resources to a label. Ask the user to confirm the assignments before executing. Do NOT use this for creating labels (use create_label) or viewing assignments (use get_label_assignments).

Use this when the user wants to see available DataHub datasets. Returns a list of datasets with metadata. Do NOT use this for billing data (use run_query) or assets (use list_assets).

Use this when the user wants to view details of a specific DataHub dataset by its ID. Returns full dataset metadata and schema. Do NOT use this for listing all datasets (use list_datahub_datasets) or cost queries (use run_query).

Use this when the user wants to create a new DataHub dataset. Ask the user to confirm the dataset name and description before executing. Do NOT use this for viewing datasets (use list_datahub_datasets) or sending events (use send_datahub_events).

Use this when the user wants to modify an existing DataHub dataset's description. The dataset name is required to identify the dataset; only the description can be changed. Ask the user to confirm the changes before executing. Do NOT use this for creating datasets (use create_datahub_dataset) or listing datasets (use list_datahub_datasets).

Use this when the user wants to send DataHub events for ingestion (1–50,000 events per call). Each event requires a provider name and an RFC 3339 timestamp, and can optionally include dimensions and metrics. Ask the user to confirm the event count and provider details before executing. Data becomes available in Cloud Analytics within ~15 minutes. Do NOT use this for creating datasets (use create_datahub_dataset) or viewing datasets (use list_datahub_datasets).

Use this when the user wants to find architecture diagrams or cloud infrastructure diagrams. Returns matching diagram files. Do NOT use this for cost analysis (use run_query) or incidents (use get_cloud_incidents).

Use this when the user wants to see their cloud spending budgets or check budget status. Returns a paginated list of budgets with names, amounts, and utilization. Do NOT use this for cost analysis (use run_query) or spending alerts (use list_alerts).

Use this when the user wants to view the details and current utilization of a specific budget. Accepts either the budget ID or a partial name (case-insensitive). Do NOT use this for listing all budgets (use list_budgets) or cost analysis (use run_query).

Use this when the user wants to create a new cloud budget with spending limits and alert thresholds. Requires budget name, currency, type, and start period. Ask the user to confirm the budget parameters before executing. Do NOT use this for viewing existing budgets (use list_budgets or get_budget) or creating alerts (use create_alert).

Use this when the user wants to modify an existing budget. Supports partial updates. Ask the user to confirm the changes before executing. Do NOT use this for viewing budgets (use list_budgets) or creating new budgets (use create_budget).

Use this when the user wants to see calendar annotations or notes on cost data. Returns a list of annotations. Do NOT use this for labels (use list_labels) or alerts (use list_alerts).

Use this when the user wants to view details of a specific annotation. Accepts either the annotation ID or a partial content match (case-insensitive). Do NOT use this for listing all annotations (use list_annotations) or labels (use list_labels).

Use this when the user wants to add a new annotation to mark a specific date or event in cost data. Ask the user to confirm the annotation details before executing. Do NOT use this for creating labels (use create_label) or alerts (use create_alert).

Use this when the user wants to modify an existing annotation. Ask the user to confirm changes before executing. Do NOT use this for creating new annotations (use create_annotation) or labels (use update_label).

Returns a list of commitment contracts from the DoiT Commitment Manager. These are Enterprise Discount Program (EDP) agreements — negotiated minimum spend or usage commitments between the customer and a cloud provider (Google Cloud, AWS, or Azure) .

Returns details of a specific Enterprise Discount Program (EDP) commitment contract, identified by its ID. Includes the full breakdown of commitment periods, per-period contracted values, and current spend attainment against the committed amount.

Ask DoiT AVA, the cloud cost and infrastructure expert, a question about the user's DoiT account, cloud spending, anomalies, or optimization opportunities. AVA has access to the customer's billing data, usage patterns, and DoiT-specific features. Use this for DoiT or cloud-specific questions only — not for general-purpose AI queries. Note: AVA can take a long time to respond for complex questions. If it does not respond in time, a clear error is returned with guidance to retry or simplify the question.

Finalizes a pending write action (e.g. creating, updating, or deleting a resource) that was previously staged by another tool. Only call this after the user has explicitly confirmed the action summary returned by the previous tool call. If the user declined, do not call this tool — the token will expire automatically. Pass the token exactly as it was returned.