Skip to main content
Glama

AICTIONBOT™ Werkbank

Sustainability evidence questions for suppliers by category, and a check of the answers against required evidence (no rating, no seal)

esg_questionnaire
Read-onlyIdempotent

AICTIONBOT™ supplier evidence questions by KULIC Advisory, built on the Execution Toolkit template T29 (sustainable procurement). From the category (e.g. packaging, logistics, cleaning, IT, electronics, chemicals, wood and paper, textiles, food, energy, construction) it compiles the matching questions: six base questions for every supplier (code of conduct, working conditions in the supply chain, environmental management, greenhouse gas data, integrity, contact person) plus modules per category, each with the evidence to ask for. With a supplier's answers it lists unanswered questions, answers without evidence and answers that were no, as topics for the supplier meeting. No rating, no seal, not legal advice. Deterministic, no AI, nothing stored. 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": "esg_questionnaire"
  }
}

Input Schema

NameRequiredDescriptionDefault
answersNoOptional supplier answers: id (e.g. B1), answer, evidence (yes/no or name of the document).
categoryNoCategory or categories in words.
languageNoLanguage of the answer. Default de.
categoriesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, closed-world, non-destructive, and the description adds real context beyond them: deterministic, no AI, nothing stored, no rating or seal, not legal advice, plus sign-in and licence requirements with a free tier of one check per connection every 30 days. Auth prerequisites and the absence of persistence are exactly the kind of behavioral facts an agent needs.

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 content is front-loaded but delivered as one dense paragraph mixing branding ('AICTIONBOT™ ... KULIC Advisory ... template T29'), category lists, mode descriptions, disclaimers, and licence details. Most sentences carry useful information, but the vendor/branding preamble and legal caveats could be trimmed or split for scannability.

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 compensates by enumerating what comes back: matching questions with the evidence to ask for, and the three answer-gap categories. All parameters are optional and the licence/rate-limit conditions are disclosed; only the category vs. categories distinction remains unresolved.

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 75% and the description reinforces what the schema already says: category examples (packaging, logistics, IT, chemicals...) and the base questions plus per-category modules. However it never clarifies the difference between the scalar 'category' and the 'categories' array (max 10), which is the one genuinely ambiguous parameter, so it only partly compensates.

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?

States a concrete verb-and-resource pair: compiling category-specific supplier evidence questions plus a gap check of supplied answers. The two operating modes (category-only vs. category+answers) are spelled out, though the tool is not explicitly contrasted against any sibling by name.

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?

It effectively describes two invocation patterns: give a category to get the question set, add answers to get a list of unanswered questions, answers lacking evidence, and 'no' answers as meeting topics. There is no explicit guidance on when not to use it or which sibling to pick instead, but the calling context is clear.

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.