Skip to main content
Glama

AICTIONBOT™ Werkbank

Contract comparison: an old and a new version of a contract, section by section, with changed, new and removed clauses and the figures before and after

compare_contracts
Read-onlyIdempotent

AICTIONBOT™ contract comparison by KULIC Advisory (tool 56). Takes the full text of the old and the new version of a contract or of terms and conditions. Splits both into sections (§, numbered clauses, articles or paragraphs), matches them by wording, number and similarity and returns per section: unchanged, renumbered only, changed (with the sentences before and now and the figures, deadlines and dates that differ), new or removed. Changes to price, payment and discount, term and termination, liability, penalties, warranty, non-solicitation, confidentiality, jurisdiction and travel expenses are marked red, as is new strict wording such as unlimited, excluded or automatic. Ends with ready questions for the other side. It shows what changed in the wording, not what it means legally; for a legal view of one contract use review_contract. Deterministic, no AI, nothing stored. Not legal advice. 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": {
      "old_text": "<old_text>",
      "new_text": "<new_text>"
    },
    "name": "compare_contracts"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage of the answer. Default de.
new_textYesFull text of the new version.
old_textYesFull text of the old (previous) version.

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 and closed-world, and the description adds genuinely new behavior: deterministic with no AI, nothing stored, red-flagging of specific clause categories and strict wording, closing questions for the counterparty, and a scope limit ('shows what changed in the wording, not what it means legally'). The licensing/free-quota note is the kind of operational constraint 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 front-loaded and dense with useful detail, but the opening brand string 'AICTIONBOT™ contract comparison by KULIC Advisory (tool 56)' and the repeated trademark notices are low-value noise for an agent. The second sentence is a long run-on packing matching logic, output categories and highlight rules into one breath.

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 by describing the returned per-section categories, the highlighted clause types, and the trailing questions. For a three-parameter, closed-world read tool, nothing an agent needs to invoke it correctly is missing.

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 both text parameters and the language enum are already documented; baseline 3 applies. The description only restates that the inputs are the full text of each version (and that T&Cs are acceptable input), which adds slight but not substantive meaning beyond the schema.

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 — comparing the full text of an old and a new contract version section by section — and enumerates the output categories (unchanged, renumbered, changed, new, removed). It explicitly distinguishes itself from review_contract, so an agent can route 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 a clear when-to-use condition (two versions of the same contract or T&Cs, full text required) and an explicit alternative with the condition that selects it: 'for a legal view of one contract use review_contract'. It also states the access prerequisite (licence or free 30-day check via 'Connect without a licence'), which governs whether a call will succeed at all.

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.