Skip to main content
Glama

AICTIONBOT™ Werkbank

Early warning check for a supplier list: red, yellow or green by KULIC Advisory's rules L-01 to L-10, plus sanctions screening

screen_supplier_risk
Read-onlyIdempotent

AICTIONBOT™ early warning check by KULIC Advisory, built on the Execution Toolkit frame T31 (supplier resilience) and the supplier check of the Werkbank. For each supplier the user passes the warning signals observed (L-01 asks for prepayment or shorter payment terms, L-02 partial deliveries and postponed dates pile up, L-03 leadership changes or contacts hard to reach, L-04 complaints rising on a proven part, L-08 high price increase shortly after an agreement, L-09 new owner, office, name or bank account, L-10 insolvency filed) and amplifiers (L-05 own tools at the supplier without a list, L-06 single source for a critical part, L-07 own volume is a large share of the supplier's revenue). Returns per supplier a light: yellow for one signal or several in the same field; red for signals from two fields, a signal with an amplifier, price jump with prepayment, L-09 with a sanctions match, or L-10; green if no signal is given (which does not mean safe). With the reasons, what to do per rule, the date to check again, and a screening of each name against the EU, UN, US and UK sanctions lists (up to 15 names per call; set screen_sanctions false for up to 25 without screening). Rules signed off by Dario Kulić. 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": {
      "suppliers": "<suppliers>"
    },
    "name": "screen_supplier_risk"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoReference date, YYYY-MM-DD. Default today.
languageNoLanguage of the answer. Default de.
suppliersYesOne object per supplier: name, signals (array of rule ids such as ["L-01", "L-06"]); instead of signals the keys prepayment, delays, leadership_change, complaints_rising, price_jump, new_owner_or_bank, insolvency, tools_without_list, single_source, high_dependency may be set to yes.
screen_sanctionsNoScreen each name against the sanctions lists. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, and the description adds substantial context beyond that: deterministic with no AI, nothing stored, sign-in/licence requirements, a 30-day free check per connection, and hard per-call name caps that change when screening is disabled. These are exactly the operational facts an agent needs before calling.

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?

Everything is delivered as a single dense block with a long parenthetical enumerating ten rules, which makes it hard to scan for the decision logic. Some framing material (AICTIONBOT™, Execution Toolkit frame T31, Werkbank) and the sign-off attribution add more brand texture than operational value, though the core content is front-loaded.

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?

There is no output schema, so the description carries the return contract and does so fully: per-supplier light, the reasons, the recommended action per rule, the next check date, and any sanctions match. Combined with the input expectations and licence constraints, an agent has everything needed to call and interpret it.

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 100%, so the baseline is 3, but the description genuinely earns more by defining what the opaque rule IDs in the signals array mean (L-01 prepayment pressure, L-02 delivery slippage, L-09 ownership/bank change, L-10 insolvency, etc.) — information absent from the schema. It also clarifies the interaction between screen_sanctions and the name cap. as_of and language are left to the schema.

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 — an early warning check over a supplied supplier list producing a red/yellow/green light per supplier according to named rules L-01 to L-10 — plus sanctions screening. That is clearly distinguishable from the sibling screen_sanctions, which screens names only, because this tool's verdict logic is described in detail.

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 explains the operating context well: the user passes the observed warning signals/amplifiers per supplier, and the capacity trades off against screening (15 names with screening, 25 with screen_sanctions=false). It also states the licence/sign-in requirement and the free tier. What it lacks is an explicit statement of when to reach for this tool versus alternates such as screen_sanctions alone, or any 'do not use when' exclusion.

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.