Skip to main content
Glama

AICTIONBOT™ Werkbank

Compare two or three supplier offers like a buyer (AICTIONBOT™ offer comparison)

compare_offers
Read-only

Needs the user's AICTIONBOT™ Werkbank licence; each call uses one AI analysis from the licence quota. Compares 2 or 3 supplier offers for the buyer: whether they are comparable, total price as stated, what is included, what is missing or unclear, extra and hidden costs, risks, a criterion-by-criterion comparison and questions to send to each supplier before deciding. Numbers are copied exactly from the offers, never invented. Pass the text of each offer (extract text from PDFs first). The texts are processed for this answer only and are not stored by KULIC Advisory.

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": "compare_offers"
  }
}

Input Schema

NameRequiredDescriptionDefault
offersYesThe offer texts, one string per offer, labelled A, B, C in this order.
languageNoLanguage of the answer: de, en, fr, es, pt or zh. Default de.
what_is_boughtNoOptional: what is being bought, in one sentence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / language / enum
      Previous value: -[
      -  "en",
      -  "de",
      -  "fr",
      -  "es",
      -  "pt",
      -  "zh"
      -]New value: +[
      +  "en",
      +  "de",
      +  "fr",
      +  "es",
      +  "pt",
      +  "zh",
      +  "hr",
      +  "sr"
      +]
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing a licence prerequisite, a per-call quota cost (important because idempotentHint is false — each repeat call costs an analysis), a privacy statement that texts are processed only for this answer and not stored, and a fidelity guarantee that numbers are copied exactly and never invented. All of this is consistent with readOnlyHint=true and destructiveHint=false.

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

Conciseness4/5

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

A single dense paragraph with no filler; the licence/quota prerequisite and the privacy note are front- and back-loaded appropriately around the core capability statement. It could be split into 'what it does / what it needs / what it returns' for faster scanning, but nothing is redundant.

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 must carry the return contract — and it does, itemising every section of the answer including the criterion-by-criterion table and the supplier question list. Combined with the licence, quota, privacy and input-preparation notes, an agent has everything needed to call this correctly and set user expectations.

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 all three parameters are already documented, which sets the baseline at 3. The description adds real handling guidance for 'offers' (pass the text, extract from PDFs first, 2–3 offers) but says nothing about the ordering/labelling contract, the language default, or how what_is_bought changes the output.

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?

Names a specific verb and resource ('Compares 2 or 3 supplier offers for the buyer') and enumerates the exact analysis produced: comparability, stated total price, inclusions, gaps, hidden costs, risks, criterion-by-criterion comparison and supplier questions. That is far more than a restatement of the name. It stops short of naming a sibling (e.g. score_offers or compare_offer_rounds), so the boundary with neighbouring comparison tools is left to inference.

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 clear operating context: it is a pre-decision buyer comparison, it requires the user's licence and consumes one AI analysis per call, and inputs must be offer text with PDFs extracted first. What it does not do is state when to pick this over the many other compare_* siblings; there is no exclusion or routing sentence.

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.