Skip to main content
Glama

AICTIONBOT™ Werkbank

Offer against contract: is what was negotiated really in the contract? Figures and deadlines per topic side by side, agreed points ticked off, message to the other side

compare_offer_to_contract
Read-onlyIdempotent

AICTIONBOT™ offer against contract by KULIC Advisory (tool 57). Takes the text of an offer (or the last negotiated version) and the text of the contract that is about to be signed, and optionally a list of agreed points, one per line. Compares the figures, deadlines and dates per topic (price, payment and discount, term and termination, liability, penalty, warranty, non-solicitation, confidentiality, jurisdiction, travel expenses): match, different, in the offer but missing in the contract, only in the contract. Each agreed point is checked against the contract. Ends with a ready message to the other side and the next step. Deterministic, no AI, nothing stored. Not legal advice. To compare two versions of the same contract use compare_contracts. 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": {
      "contract_text": "<contract_text>"
    },
    "name": "compare_offer_to_contract"
  }
}

Input Schema

NameRequiredDescriptionDefault
agreedNoOptional: points agreed in the negotiation, one per line, for example 'Payment terms 30 days net'.
languageNoLanguage of the answer. Default de.
offer_textNoFull text of the offer or of the last negotiated version.
contract_textYesFull text of the contract to be signed.

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 cover read-only, idempotent, non-destructive and closed-world, and the description adds materially more: deterministic, no AI, nothing stored, not legal advice, plus the auth/licence requirement and the 30-day free-check limit. That is exactly the kind of context annotations cannot express.

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 substantive content is well organized and front-loads the comparison outcome categories, but the opening is branding and boilerplate ('AICTIONBOT™ ... (tool 57) by KULIC Advisory') that does no work for an agent. The parenthetical topic list is long but earns its place by telling the agent what gets compared.

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, and the description compensates fully: it names the four result categories, the per-topic breakdown, the agreed-point check, and the closing message plus next step. An agent knows what comes back and how much to trust it (deterministic, nothing stored, not legal advice).

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 four parameters including the one-per-line format for agreed points and the language default. The description largely restates those meanings ('text of an offer (or the last negotiated version)', 'contract that is about to be signed') without adding format or validation detail, 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?

States a specific verb and resource (compare an offer's text against the contract text about to be signed) and enumerates the topics compared plus the four comparison outcomes. It also explicitly distinguishes itself from the sibling compare_contracts, so an agent can route correctly 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 Guidelines5/5

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

Gives explicit when-to-use conditions (offer or last negotiated version vs. contract about to be signed) and names the alternative for the different case: 'To compare two versions of the same contract use compare_contracts.' It also states the licensing gate and the free fallback path ('Connect without a licence'), which an agent needs before calling.

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.