Skip to main content
Glama

AICTIONBOT™ Werkbank

Review a contract or terms and conditions from the buyer side (AICTIONBOT™ clause radar)

review_contract
Read-only

Needs the user's AICTIONBOT™ Werkbank licence; each call uses one AI analysis from the licence quota. Reviews a contract or general terms and conditions the buyer is asked to sign, clause by clause (term, renewal, notice, price adjustment, payment, liability, warranty, penalties, acceptance, exclusivity, data protection, jurisdiction). Returns a summary and, per clause, the exact reference, the plain-language meaning, a rating (ok, pruefen = check, kritisch = critical), why it matters for the buyer and a counter-proposal; deadline dates only when the start date is known. Also returns datenblatt, the key data of the contract as stated (supplier, subject, target value, payment terms, items) for entry into an ERP or accounting system. Pass the full contract text (extract text from PDFs or images first). Not legal advice. The text is processed for this answer only and is 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": {
      "contract_text": "<contract_text>"
    },
    "name": "review_contract"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage of the answer: de, en, fr, es, pt or zh. Default de.
contract_textYesFull text of the contract or the terms and conditions.
contract_startNoOptional contract start, YYYY-MM-DD, to compute notice dates.

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

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and destructiveHint=false, and the description adds real behavioral context beyond them: one AI analysis is consumed from the licence quota per call, the text is processed for this answer only and not stored, and notice deadlines appear only when the start date is known. It also flags 'Not legal advice', setting the expectation for how the output should be treated. No contradiction with the annotations.

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?

The paragraph is dense but every sentence carries information: quota cost, reviewed clause list, output shape, datenblatt, input prerequisite, disclaimer, privacy. The main structural weakness is that the licence/quota constraint precedes the statement of purpose, so the core 'what this does' is not strictly front-loaded, and the long clause enumeration could be tightened.

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 does the heavy lifting and covers the return payload well (summary, per-clause reference, plain-language meaning, rating scale, buyer impact, counter-proposal, plus datenblatt fields). Minor gaps remain: it says nothing about behavior when text approaches the 60,000-character limit or when quota is exhausted.

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 schema already defines all three parameters; the description adds behavior-level meaning by clarifying that contract_text must be the full text (extracting from PDFs/images first is the caller's job) and that contract_start determines whether deadline dates are produced at all. That is a genuine value-add over the schema's bare 'compute notice dates' wording.

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?

The description states a specific verb and resource ('Reviews a contract or general terms and conditions the buyer is asked to sign, clause by clause') and enumerates the clause categories covered, so the agent knows exactly what scope of work is performed. It never names a sibling tool (compare_invoice_to_contract, check_contracts, create_contract_draft), so routing among the contract-family tools is left to inference even though the buyer-side clause review scope is distinctive.

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?

Usage context is clear: it applies to contracts the buyer is asked to sign, and it gives a concrete prerequisite ('Pass the full contract text (extract text from PDFs or images first)') plus the licence requirement. It stops short of explicit when-not conditions or pointing to alternatives for drafting, comparing, or deadline-only calculation.

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.