Skip to main content
Glama

AICTIONBOT™ Werkbank

Switch-over check for a new system or a new supplier: dated checklist, readiness traffic light, gaps and a Q&A sheet for staff

check_switchover
Read-onlyIdempotent

AICTIONBOT™ switch-over check by KULIC Advisory (tool 42), built on the Execution Toolkit template T06 (implementation tracker). kind system (new ERP or purchasing system) or supplier (switch to a new supplier), name, go_live date. Without a list it returns a 12-point checklist dated from the go-live (data, open orders, roles and approvals, training, test, supplier information, cut-over, post-launch support; or contract and notice, supplier set-up, samples, open orders, stock, tools and moulds, first delivery, first rating). With the team's own list (item, area, owner, due, status) it rates readiness red, yellow or green, lists blocked and overdue items, items without owner or date, and checklist points missing from the list. Always adds questions and answers for staff. 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_switchover"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNosystem for a new system, supplier (lieferant) for a new supplier. Default system.
nameNoWhat is being switched, e.g. new purchasing system.
as_ofNoReference date, YYYY-MM-DD. Default today.
itemsNoOptional own list: item, area, owner, due, status (open, in progress, done, blocked).
go_liveNoGo-live date, YYYY-MM-DD or DD.MM.YYYY.
languageNoLanguage of the answer. Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
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, but the description adds real context beyond them: deterministic with no AI, nothing stored, and an explicit access model (AICTIONBOT Werkbank licence, otherwise one check per connection per 30 days via 'Connect without a licence'). That licensing and rate-limit disclosure is exactly the kind of information annotations cannot convey; only the marketing framing at the start dilutes it.

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 core content is front-loaded after an opening clause of branding and template provenance ('AICTIONBOT™ ... KULIC Advisory (tool 42) ... template T06'), which consumes attention without helping selection. The long parenthetical enumerations of checklist points are informative but dense and could be trimmed without losing decision-relevant content.

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?

There is no output schema, so the description carries the return-value burden and does so competently: checklist, traffic light, blocked/overdue items, ownerless and dateless items, missing checklist points, plus the always-included Q&A. Authentication and the free-tier limit are covered; the only shortfall is that output format and shape are described only qualitatively.

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 documents all six parameters including enum meanings and default values, making 3 the baseline. The description does add outcome-level meaning: go_live anchors the dates in the generated checklist, and supplying items (item, area, owner, due, status) switches the tool into rating-and-gap mode, which is a genuine semantic addition rather than restatement.

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?

States a specific verb and resource: a switch-over check for either a new system (ERP/purchasing) or a new supplier, with named inputs (kind, name, go_live). It enumerates exactly what it returns (12-point dated checklist, red/yellow/green readiness rating, gap list, staff Q&A), so the resource is unambiguous. It does not, however, contrast itself with nearby siblings such as rate_supplier or ai_readiness, so the agent must infer that boundary.

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 through the two input modes: without a list you get a fresh dated checklist, with the team's own list you get a readiness rating and gap analysis. That is a clear behavioural split, but there is no explicit when-to-use or when-not guidance against alternative tools, and no prerequisites such as 'do this before rate_supplier' are stated.

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.