Skip to main content
Glama

export_kpi_report_bundle

Generate printable PDF and styled Excel KPI report bundles with SHA-256 checksums, optional summaries and detail tabs, PII stripping, and dry-run planning.

Instructions

Render deterministic KPIs into printable PDF and styled Excel files.

Args: computed_kpis: ComputeProcessKpisResult dict (or JSON string). output_dir: Destination folder inside PBI_WORKSPACE_ROOT. report_title: Printable report header/title. summary_text: Optional verified executive summary text to embed in PDF/XLSX. detail_rows_path: Optional source Excel/CSV to include as bounded detail tab. detail_sheet_name: Optional worksheet name for detail_rows_path. formats: Output formats subset of ["xlsx", "pdf"]. include_pii_columns: Preserve PII-named columns in detail tab when True (default False). dry_run: Plan artifact paths without writing files when True (default True).

Returns: Dict with generated file paths, SHA-256 checksums, stripped PII columns, and status.

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": {
      "computed_kpis": "<computed_kpis>",
      "output_dir": "<output_dir>"
    },
    "name": "export_kpi_report_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
formatsNo
output_dirYes
report_titleNoReporte de Control y KPIs
summary_textNo
computed_kpisYes
detail_rows_pathNo
detail_sheet_nameNo
include_pii_columnsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.25.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it states the default dry_run=True means no files are written, that PII-named columns are stripped unless include_pii_columns=True, that detail rows are bounded, and that output is confined to PBI_WORKSPACE_ROOT. It omits overwrite behavior for existing files and any size or permission constraints.

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?

Front-loaded one-line purpose followed by tidy Args/Returns blocks that map cleanly to the schema. The Returns block is partly redundant with the output schema, but overall there is little wasted wording for a 9-parameter tool.

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?

For a 9-param file-generating tool with an output schema, the description covers inputs, safety defaults (dry run, PII stripping), write location, and return contents (paths, checksums, status). Missing only overwrite semantics and the dependency on a prior compute_process_kpis call.

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 description coverage is 0% across 9 parameters, so the description must compensate, and the Args block documents every parameter including defaults (formats subset, PII default False, dry_run default True) and path constraints. computed_kpis is only typed, not explained in shape or origin, which keeps it from a 5.

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?

"Render deterministic KPIs into printable PDF and styled Excel files" gives a specific verb (render) and concrete artifacts (PDF, XLSX), so the agent knows exactly what comes out. It does not name or differentiate from any sibling (e.g., compute_process_kpis, which produces the input), so it stops short of a 5.

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?

There is no explicit when-to-use statement, no prerequisite call-out that computed_kpis comes from compute_process_kpis, and no mention of alternatives. Usage is only implied by the dry_run default of True, which signals a plan-first-then-write workflow.

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