Skip to main content
Glama

AICTIONBOT™ Werkbank

Revised offer: is round 2 really cheaper? The difference split into price, quantity, removed and new items, with questions for the supplier

compare_offer_rounds
Read-onlyIdempotent

AICTIONBOT™ revised offer check by KULIC Advisory (tool 59). Takes the items of a first offer and of the revised offer from the same supplier and matches them by description, otherwise by item number. Splits the difference between the two totals into four parts: lower or higher prices of the same items, changed quantities, removed items and new items. Says whether the reduction is real (from prices) or comes from a smaller scope, lists every item that became more expensive, every removed and added item and every changed quantity, and ends with ready questions for the supplier and the next step. Pass two arrays (old_rows for round 1, new_rows for round 2) or one array rows with a round column (1 or 2). Deterministic, no AI, nothing stored. To compare offers from different suppliers use compare_offers or score_offers. 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": "compare_offer_rounds"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsNoAlternative to old_rows and new_rows: one list with a round column (1 or 2) plus the columns above.
languageNoLanguage of the answer. Default de.
new_rowsNoRound 2 with the same columns.
old_rowsNoRound 1: position (item number), description, quantity, unit_price, optionally total. German column names work too.

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, closed-world behavior, yet the description still adds real value: deterministic, no AI, nothing stored, matching order (description first, then item number), the four-part decomposition of the difference, the explicit item-level outputs, and the licence/rate-limit terms (one free check per connection every 30 days).

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 purpose leads, but the opening branding string 'AICTIONBOT™ revised offer check by KULIC Advisory (tool 59)' and the lengthy licence paragraph crowd out the analytical content, and the middle is a single long chain of clauses. It is information-dense but not tight.

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?

For a tool with no output schema, the description fully specifies what comes back: the four-way split, a real-versus-scope verdict, the lists of increased/removed/added items and changed quantities, plus supplied questions and a next step. An agent knows both the inputs and the shape of the answer before calling it.

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 coverage is 100%, so the two input shapes (old_rows + new_rows versus a single rows array with a round column), the column expectations, and the language enum are already documented. The description restates the alternative input modes and the German column-name tolerance without adding format or unit detail beyond the schema, so the baseline 3 applies.

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?

The description states a specific operation on a specific resource: matching the items of a first offer against a revised offer from the same supplier and splitting the total delta into four named components. It also explicitly separates itself from compare_offers and score_offers by noting those are for offers from different suppliers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives the precondition (two rounds from the same supplier), names the alternative tools for the different-supplier case, and states the licence/sign-in requirement with the free fallback. The only mild gap is that it does not say what happens when the two rounds cannot be matched, but the routing guidance itself is explicit.

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.