Skip to main content
Glama

AICTIONBOT™ Werkbank

Question sheet for your own purchasing help: collected questions sorted by topic, duplicates merged, open ones marked

sort_questions
Read-onlyIdempotent

AICTIONBOT™ question sorter by KULIC Advisory (tool 73). Takes the questions people ask about buying (from training, mail, chat or notes), each with its answer where one exists, and returns a question sheet: sorted into nine fixed topics (access, ordering, approval, delivery, invoice, suppliers, contracts, who to ask, other), near-identical questions merged with a count, the answer next to each question, open questions marked with the Workbench tool that helps, the topic with the most questions and the next step. Deterministic keyword rules, no AI, nothing stored. It sorts your questions and answers and does not write answers itself. To find recurring causes in a list of problems use analyse_issues. 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": {
      "rows": "<rows>"
    },
    "name": "sort_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesOne row per question: question, answer (may be empty). German column names work too (frage, antwort).
languageNoLanguage of the answer. Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the bar is lower, yet the description still adds real behavior: deterministic keyword rules with no AI, nothing stored, and a licence gate with a 30-day free check. It does not cover limits such as the 5000-row cap or what happens when the rows list is malformed.

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 core content sits inside one very long run-on sentence, preceded by branding noise ('AICTIONBOT™ question sorter by KULIC Advisory (tool 73)') that carries no operational value. Enumerating the nine topics is useful but adds bulk; the licence paragraph is well separated.

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 must explain returns, and it does reasonably well: sorted sheet, merged duplicates with counts, marked open questions, dominant topic and next step. The licence prerequisite is disclosed. Minor gaps remain on row limits and error behavior for a tool accepting up to 5000 rows.

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 100%, so the baseline is 3. The description adds only source context for the rows ('from training, mail, chat or notes') and never mentions the language parameter, so it does not meaningfully exceed what the schema already documents.

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 ('question sorter' that takes buying questions and returns a sorted question sheet) and enumerates what the output contains: nine fixed topics, merged duplicates with counts, answers adjacent, open questions flagged. It also names the sibling it is not ('To find recurring causes ... use analyse_issues'), so an agent can distinguish it without opening the schema.

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?

Gives an explicit routing rule to one alternative (analyse_issues for recurring causes) and states the licence/sign-in context plus the free-without-licence path. It stops short of a full when-not-to-use statement or naming other sorting siblings like sort_categories.

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.