Skip to main content
Glama

check_report_data_consistency

Reconcile expected or source-file KPIs against a live Power BI dataset, flag discrepancies beyond tolerance, and return per-KPI consistency details.

Instructions

Reconcile expected or source-file KPIs against a live Power BI dataset.

Args: workspace_id: Power BI / Fabric workspace GUID. dataset_id: Power BI / Fabric dataset GUID. source_path: Optional Excel/CSV source file for independent baseline calculation. sheet_name: Optional Excel worksheet name. catalog_path: Optional YAML KPI catalog path. expected_kpis: Optional dict (or JSON string) of explicit expected KPI numbers. tolerance_pct: Allowed relative discrepancy ratio before flagging mismatch (default 0.001). as_of_date: Optional ISO date YYYY-MM-DD for source baseline calculation. query_executor: Optional injected DAX query executor callable for testing. fabric_client: Optional injected FabricClient for testing. auth_mode: Optional auth mode override. tenant_id: Optional Entra ID tenant. client_id: Optional Entra ID client ID.

Returns: Dict with overall consistency flag and per-KPI source vs dataset discrepancy details.

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": {
      "workspace_id": "<workspace_id>",
      "dataset_id": "<dataset_id>"
    },
    "name": "check_report_data_consistency"
  }
}

Input Schema

NameRequiredDescriptionDefault
auth_modeNo
client_idNo
tenant_idNo
as_of_dateNo
dataset_idYes
sheet_nameNo
source_pathNo
catalog_pathNo
workspace_idYes
expected_kpisNo
fabric_clientNo
tolerance_pctNo
query_executorNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.25.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations the description carries the full burden, and it does disclose the return shape (overall flag plus per-KPI discrepancies) and the tolerance default. It does not state that the tool is read-only against the live dataset, what permissions or auth are needed despite listing auth_mode/tenant_id/client_id, or that the injected query_executor/fabric_client args are test-only seams.

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?

Purpose is front-loaded in one sentence, and the 13 param lines are largely justified given zero schema description coverage. The Returns block duplicates the existing output schema, which is the only clearly removable content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All 13 parameters are covered and the output schema means return values need no explanation, so the core is present. What is missing for a tool this complex is decision guidance among the three baseline sources and the read-only/auth behavior of querying a live dataset.

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 0% across 13 parameters, so the Args block is the only source of meaning — and it documents every one, adding value beyond the schema such as 'dict (or JSON string)' for expected_kpis and the relative-discrepancy meaning of tolerance_pct. It does not clarify accepted values for auth_mode or the expected_kpis dict shape.

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 states a specific verb and resource: 'Reconcile expected or source-file KPIs against a live Power BI dataset.' That is distinct from audit_model_and_report or execute_dax_query, though the description never names a sibling to sharpen the boundary.

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

Usage Guidelines2/5

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

It never says when to pick this over audit_model_and_report or run_dax_regression, nor when to prefer expected_kpis versus source_path versus catalog_path as the baseline. The parameter blurbs hint at three baseline modes but the agent must infer which to choose and whether they combine.

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