Skip to main content
Glama

AICTIONBOT™ Werkbank

Process lever: current and target minutes and rework per process step, turned into hours, full-time equivalents and euros per year

process_lever
Read-onlyIdempotent

AICTIONBOT™ process lever by KULIC Advisory, built on the Execution Toolkit template T05 (process improvement). Takes the process steps with cases per year (or per month), minutes now and in the target state, and optionally rework rates and rework minutes, plus the hourly cost. Returns hours per year now and in the target state, hours saved, full-time equivalents and euros per year, the steps with the largest lever, steps that would get slower, the change of optional KPIs (baseline to target) and the inputs to continue in build_business_case. Example values (hourly cost 50 euros, 1,600 productive hours per full-time equivalent) are marked as such when the user gives none. 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

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": {
      "steps": "<steps>"
    },
    "name": "process_lever"
  }
}

Input Schema

NameRequiredDescriptionDefault
kpisNoOptional KPIs with kpi, baseline, target.
stepsYesSteps: step, cases (per year) or cases_per_month, minutes_now, minutes_target, error_rate_now (percent), error_rate_target (percent), rework_minutes.
languageNoLanguage of the answer. Default de.
hourly_costNoHourly cost in euros. Default 50 (marked as example).
productive_hours_per_fteNoProductive hours per full-time equivalent and year. Default 1,600 (marked as example).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description goes further by disclosing determinism, no AI involvement, no storage, and the licensing gate with a free 30-day check per connection. It also warns that default values (50 euros, 1,600 hours) are flagged as examples when the user supplies none, which is real behavioral context an agent would otherwise not know. It stops short of saying anything about runtime, limits on step count, or how failures are reported.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two long sentences, but each clause carries information: inputs, outputs, defaults, access model. It is front-loaded with what the tool consumes and produces, and the licence detail sits last. The vendor/template branding in the opening clause is the only element that does not earn its place, which is minor.

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 must explain returns, and it does so thoroughly (hours now/target, hours saved, FTE, euros, largest levers, steps that get slower, optional KPI change, and hand-off inputs for build_business_case). It also covers access requirements and default-value semantics. Gaps are minor: no mention of the 100-step/20-KPI caps or what a validation error looks like.

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%, so the schema already defines steps, kpis, language, hourly_cost and productive_hours_per_fte, including the default-and-marked-as-example behavior. The description adds only the high-level framing that cases may be per year or per month and that rework rates/minutes are optional, plus the meanings of outputs. Baseline 3 is appropriate given the schema does the heavy lifting.

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 description names a concrete computation on a concrete resource: it takes process steps with cases, minutes now/target, rework rates and hourly cost and returns hours per year, hours saved, FTEs and euros per year. The verb is implicit ("takes ... Returns") rather than a clean verb+resource phrase, and the branding/template sentence (AICTIONBOT™, KULIC Advisory, template T05) does no differentiation work. It does, however, clearly separate this tool from build_business_case by naming the latter as the downstream consumer.

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?

Usage is implied rather than stated: the caller learns this is a process-improvement lever and that its outputs feed build_business_case, which gives some routing signal. There is no explicit statement of when to use this versus the other analysis tools (compare_scenarios, analyse_spend, check_kpis, assess_team), and no when-not guidance. The licence/one-free-check note tells the agent about access conditions rather than about selection.

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.