Skip to main content
Glama

AICTIONBOT™ Werkbank

Check their NDA: a non-disclosure agreement from the other side against twelve standard points, with what goes beyond the usual and what is missing

check_nda
Read-onlyIdempotent

AICTIONBOT™ NDA check by KULIC Advisory (tool 68). Takes the full text of a non-disclosure agreement you received and checks it by keywords against twelve standard points. Red when the text contains something that goes beyond a usual NDA: contractual penalty, non-solicitation, non-compete or exclusivity, transfer of rights to results, unlimited liability or indemnity, a duty without an end. Yellow when a usual point is missing or unclear: applies to both sides, the usual exceptions, duration (more than five years or none stated), return or deletion, disclosure to staff and advisers, exception for court and authority, law and jurisdiction. Returns each point with the sentence found in the text, the requests to make to the other side and the next step. Recognises German and English texts. Deterministic, no AI, nothing stored. Keyword based: it does not replace reading. Not legal advice. To write your own NDA use create_nda, for an AI review of a contract use review_contract. 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": {
      "text": "<text>"
    },
    "name": "check_nda"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesFull text of the non-disclosure agreement, German or English.
languageNoLanguage of the answer. Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds genuinely useful behavior: deterministic, no AI, nothing stored, and a rate-limited licence model. However, a stricter read is warranted because the free-tier limit is stated in the description while no annotation expresses throttling or auth requirements, leaving the operational contract slightly inconsistent between the two sources.

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?

Front-loaded with the verb and licensing, followed by the red-criteria list, the yellow-criteria list, then the return shape and caveats — a logical order with no filler. It is a dense single block with no paragraph separation, and the enumeration of all twelve points, while useful, makes it long for an agent to scan.

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?

No output schema exists, yet the description explains what comes back: each point with the sentence found, the requests to make to the other side, and the next step. Combined with language support, determinism, storage behavior and licensing, nothing material is missing for a 2-parameter read-only tool.

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 both parameters are documented in the schema. The description adds meaning by noting the text may be German or English and by describing what the tool returns per point, which contextualises how the text input is consumed. It does not clarify that the language parameter controls the answer language versus the detected text language, which is the one ambiguity an agent could stumble on.

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 precise verb and resource ("checks the full text of a non-disclosure agreement you received") plus the method (keyword matching against twelve standard points) and the output shape (red/yellow findings). It distinguishes itself from named siblings create_nda and review_contract, so an agent can route correctly without opening any 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 alternatives and their conditions: "To write your own NDA use create_nda, for an AI review of a contract use review_contract." It also sets scope limits ("Keyword based: it does not replace reading. Not legal advice.") and access prerequisites (licence, free tier of one check per connection every 30 days).

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.