Skip to main content
Glama

AICTIONBOT™ Werkbank

Approval matrix old against new: raised limits, new and removed approval rights, lost deputies, areas without an approver

compare_approval_matrix
Read-onlyIdempotent

AICTIONBOT™ approval matrix comparison by KULIC Advisory (tool 64). Takes the old and the new version of an approval matrix (area, level, approver, limit up to, deputy) and matches the rows by area and level. Returns the critical changes (red: a limit raised by more than 50 percent, a deputy removed, an approver who is their own deputy, an area left without an approver), the other changes (yellow: new approver, moderately raised limit, new or removed approval right), lowered limits and changed deputies for information, who may approve more than before, the questions to answer before the matrix is loaded into the system and the next step. Pass two arrays (old_rows and new_rows) or one array rows with a version column (Old or New; German: Alt or Neu). Deterministic, no AI, nothing stored. To check one matrix against the people list use check_approval_matrix. 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": "compare_approval_matrix"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsNoAlternative to old_rows and new_rows: one list with a version column (Old or New) plus the columns above.
languageNoLanguage of the answer. Default de.
new_rowsNoNew version with the same columns.
old_rowsNoOld version: area, level, approver, limit_to, deputy. German column names work too (bereich, stufe, freigeber, limit_bis, vertreter).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the description's safety burden is light. It does add genuinely non-obvious behavior: deterministic, no AI, nothing stored, licence-gated with a free 30-day check, and the exact severity thresholds (limit raised >50 percent is red). That earns a solid 3, though it stops short of describing volume behaviour for the 20,000/40,000 row caps.

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 purpose is front-loaded, but the body is one dense run-on paragraph mixing output taxonomy, input modes, branding and licensing. 'AICTIONBOT™ by KULIC Advisory (tool 64)' and the licence sales pitch do not help an agent select or invoke the tool, and the red/yellow criteria would read far better as a short list than as a comma-spliced sentence.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so by naming every output section (critical changes with their triggers, other changes, informational items, questions, next step). Combined with input shape alternatives, the sibling pointer and the auth/licence note, an agent has everything needed to call it correctly.

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 description coverage is 100 percent, so all four parameters are already documented, including the German column aliases and the version-column alternative. The description repeats rather than extends that (column names, Old/New values), adding only the matching key (area and level), which is behaviour rather than parameter meaning. Baseline 3 applies.

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?

The description states a specific verb and resource (compares old vs new approval matrices, matching rows by area and level) and enumerates exactly what it reports back: red/yellow critical changes, lowered limits, who may approve more, open questions and next step. It also explicitly distinguishes itself from check_approval_matrix, so an agent can separate the two without opening either schema.

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?

It routes the agent clearly, naming check_approval_matrix as the tool for checking a single matrix against the people list, and explains the two accepted input shapes (old_rows + new_rows, or rows with a version column). What is missing is an explicit 'when not to use' beyond that single sibling pointer, and no statement about what happens if neither input shape is supplied despite zero required parameters.

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.