Skip to main content
Glama

AICTIONBOT™ Werkbank

Score offers with weighted criteria: ranking, gap to the runner-up, the weight change that would flip the winner, suspiciously low prices

score_offers
Read-onlyIdempotent

AICTIONBOT™ offer scoring by KULIC Advisory, built on the Execution Toolkit template T11 (sourcing evaluation). Takes two or more offers with a price and scores (e.g. quality, delivery time, service, risk) and returns a weighted ranking out of 100, the gap between first and second, the tipping point (the smallest weight change that would put another offer first) and prices below 70 % of the median. Lowest price and shortest delivery time get full points, others proportionally; higher scores are better unless the criterion is price, cost, lead time, risk or defects. Without criteria the price gets 40 % and the other numeric columns share 60 %. Offers that fail must-have criteria (must_have: no) are left out. Pass the figures you read from the offers; to read offer documents use compare_offers. 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": {
      "offers": "<offers>"
    },
    "name": "score_offers"
  }
}

Input Schema

NameRequiredDescriptionDefault
offersYesOne object per offer: supplier, price, and further numeric criteria as keys or in a scores object; optional must_have (yes/no).
criteriaNoOptional criteria with weight (any scale, normalised to 100), better (higher or lower) and scale_max for scores on a fixed scale (e.g. 5 or 10). The name must match the key in the offers.
languageNoLanguage of the answer. Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial behavior beyond the readOnly/idempotent/destructive annotations: deterministic, no AI, nothing stored, and an explicit licensing/auth model including a free check per connection every 30 days. It also discloses the internal scoring rules (lowest price and shortest lead time get full points, inverted direction for cost/risk/defect criteria) and the default 40/60 weighting when no criteria are given.

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 content is dense and front-loaded on outputs, but the opening branding sentence (AICTIONBOT™, KULIC Advisory, Execution Toolkit template T11) earns nothing for an agent and the middle section packs several distinct rules into one long clause chain. Sizing is defensible for a tool with no output schema, yet the structure could be split by concern.

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 carries the return-value burden and does explain all four return types plus defaults and exclusions. Remaining gaps are minor: no note on tie-breaking, on the output's exact shape (points vs. percentages beyond 'out of 100'), or on what happens when a criterion name matches no offer key.

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, and the description earns more by explaining the default weighting that applies when criteria are omitted, the direction convention for price/cost/risk/defects, and the must_have exclusion. It does not add much beyond the schema on weight normalization or scale_max, which the schema already documents.

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?

Names a specific action and output set: weighted ranking out of 100, gap between first and second, tipping point, and prices below 70% of median. It also distinguishes itself from the sibling compare_offers, which is cast as the document-reading tool, so an agent can route between them 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?

Gives usable preconditions (two or more offers, figures already read from the documents, use compare_offers to read them) and states an exclusion rule (offers failing must-haves are dropped). It does not cover when to prefer this over other analytical siblings such as compare_scenarios, so it stops short of a full when/when-not map.

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.