Skip to main content
Glama

AICTIONBOT™ Werkbank

Check source-to-pay KPIs as a traffic light: PO coverage, invoices without PO, after-the-fact POs, cycle times, exceptions, payment on time, cash discount

check_kpis
Read-onlyIdempotent

AICTIONBOT™ S2P KPI check by KULIC Advisory, built on the Execution Toolkit template T04 (end-to-end S2P KPI dashboard). Either takes an export with one row per invoice (amount, PO number, invoice, PO, requisition, approval, due and payment dates, exception yes/no, cash discount available and taken) and calculates PO coverage by spend, share of invoices without a PO, after-the-fact POs, requisition-to-PO and invoice-to-approval cycle times (median), invoice exceptions and first-time match, payment on time and cash discount captured with the amount left on the table; or takes finished figures (kpi, actual, target) and rates them. Every figure gets red, amber or green against a target (the user's own or a stated suggestion; amber within 20 percent of the target) and the base it was calculated on. Fields that are missing are named instead of guessed. Deterministic, no AI, nothing stored. Needs sign-in: runs with an AICTIONBOT™ Werkbank licence; without a licence one check per connection every 30 days is free (sign in with “Connect without a licence”).

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": "check_kpis"
  }
}

Input Schema

NameRequiredDescriptionDefault
kpisNoAlternative to rows: finished figures with kpi, actual, target, optional better (higher or lower), unit, owner.
rowsNoInvoice rows: amount, po (number or empty), invoice_date, po_date, pr_date, approved_date, due_date, paid_date, exception (yes/no), discount_available (amount), discount_taken (amount or yes/no).
targetsNoOwn targets for the calculated figures, keys po_coverage, no_po_share, after_the_fact, pr_to_po_days, exceptions, first_time_match, invoice_to_approval_days, on_time_payment, discount_capture.
languageNoLanguage of the answer. Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: the amber threshold (within 20 percent of target), a stated default target suggestion vs. the user's own, the rule that missing fields are named rather than guessed, determinism with no AI, and that nothing is stored. It also discloses the auth/licensing requirement and the free quota of one check per connection every 30 days.

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?

Core capability is front-loaded, but the opening clause carries branding and template reference ('AICTIONBOT™ ... KULIC Advisory ... template T04') that does not help an agent select or call the tool, and the metric enumeration is packed into a single long sentence. The licensing text is useful but sits after the substance without clear separation.

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 tool with no output schema, the description adequately covers both input modes, the rating output (red/amber/green plus the base each figure was computed on), thresholds, handling of missing fields, and the licensing prerequisite. Remaining gaps are minor, such as the shape and size of the returned per-KPI table.

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%, so the schema already documents rows, kpis, targets and language. The description corroborates the column list and the two input modes but adds little beyond the schema, such as that targets may be the user's own or a suggested default. Baseline 3 applies when the schema carries the parameter detail.

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?

States a specific verb and resource ('S2P KPI check') and enumerates exactly what is computed: PO coverage by spend, no-PO share, after-the-fact POs, requisition-to-PO and invoice-to-approval cycle times, exceptions, on-time payment, discount capture. The dual input mode (invoice rows vs. finished figures) is spelled out, so an agent can tell it apart from narrower siblings such as check_discount_window or check_invoice_payment.

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

Usage Guidelines4/5

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

Gives clear context for the two supported input modes ('Either takes an export with one row per invoice ... or takes finished figures') and explains the rating behavior. It does not, however, state when to prefer this broad dashboard over the more granular sibling checks, nor any exclusion conditions.

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.