AICTIONBOT™ Werkbank

Check an approval matrix against the people list: who approves although they left, lack a role or have no deputy

check_approval_matrix

Read-onlyIdempotent

AICTIONBOT™ Freigabematrix-Prüfer by KULIC Advisory. Checks an approval matrix (area, level, approver, limits, deputy, system) against a people list (status, leaving date, absence, system role) and optional open approvals, and returns the rows that need action: approvers who left, are absent without a cover, lack a system role, missing deputies, limit gaps and overlaps, plus open approvals stuck with those people. Deterministic, no AI, nothing stored. Findings are written in German. Keys may be German (bereich, stufe, freigeber, limit_von, limit_bis, waehrung, vertreter, system; person, status, austritt, abwesend_bis, systemrolle; beleg, bereich, betrag, wartet_bei, seit) or English (area, level, approver, limit_from, limit_to, currency, deputy, system; person, status, left_on, absent_until, system_role; document, area, amount, waiting_with, since).

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": {
      "matrix": "<matrix>",
      "people": "<people>"
    },
    "name": "check_approval_matrix"
  }
}

Input Schema

Name	Required	Description
`as_of`	No	Reference date, YYYY-MM-DD. Default today.
`matrix`	Yes	Approval matrix rows.
`people`	Yes	People list. Each person: name, status (active, left, absent), left_on, absent_until, system_role (yes/no).
`language`	No
`open_approvals`	No	Optional open approvals: document, area, amount, waiting_with, since, system.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / properties / people / description

Previous value: -"People list with status (active, left, absent), left_on, absent_until, system_role (yes/no)."New value: +"People list. Each person: name, status (active, left, absent), left_on, absent_until, system_role (yes/no)."

AddedNov 2, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is done. The description adds genuine extra behavior: deterministic rule evaluation, no AI involvement, nothing stored, findings emitted in German, and dual German/English key acceptance.

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 operational content is front-loaded and the key mapping is useful, but the opening vendor line ('AICTIONBOT™ Freigabematrix-Prüfer by KULIC Advisory') is marketing that earns nothing, and the long parenthetical key lists are dense without being structured into separate lines.

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 correctly compensates by describing what comes back (action-needed rows plus stuck open approvals). Combined with annotations covering the safety profile, an agent has enough to call it correctly; only the language parameter behavior and output shape details are left fuzzy.

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 80%, so baseline would be 3, but the description earns more: the matrix, people and open_approvals arrays are declared only as generic objects in the schema, and the description supplies the actual field vocabulary for each. Gap: the language enum (de/en) is never explained and sits awkwardly against 'Findings are written in German', and as_of is not mentioned.

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 concrete verb and resource ('Checks an approval matrix ... against a people list') and enumerates exactly which findings it returns (left approvers, absence without cover, missing system role, missing deputies, limit gaps/overlaps, stuck approvals). This is clearly distinguishable from the sibling contract/invoice/deadline checkers.

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?

The description makes the use case implicit — audit an approval matrix against HR data — and notes that open_approvals is optional. However, it never states when to prefer this over a sibling tool, nor any prerequisites (e.g. data must be exported in a specific shape) or exclusions.

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

All AICTIONBOT™ Werkbank tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?