Skip to main content
Glama

AICTIONBOT™ Werkbank

Draft a request for quotation (RFQ) from the KULIC Advisory RFQ template: scope, requirements, response table, checklist, timeline, criteria, terms

create_rfq
Read-onlyIdempotent

KULIC Advisory, AICTIONBOT™ Workbench. Drafts a complete request for quotation in German or English following the Execution Toolkit template T10 (RFQ): title, RFQ number, issue and due date, buyer and contact, 1 scope and requirements, 2 commercial response table with the user's lines (description, specification, quantity, unit, delivery), 3 submission checklist and timeline with a question deadline, 4 weighted evaluation criteria (the user's own or a suggestion: price and total cost 40, quality 25, delivery 15, service 10, terms and risk 10), 5 clarifications in writing, 6 compliance and terms with payment terms, offer validity and governing law. Missing details are left as clearly marked placeholders in square brackets, never invented. Returns the full text ready to paste into an email or document, plus the link to the Excel template T10 that fill_template can fill. Deterministic, no AI, nothing stored. Working template, 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": {
      "title": "<title>"
    },
    "name": "create_rfq"
  }
}

Input Schema

NameRequiredDescriptionDefault
buyerNo
linesNoLines: description, specs, qty, unit, delivery.
scopeNoGoods or services, objective and expected outcome.
termsNo
titleYesWhat the request is about, e.g. 'Cleaning of the office building from 2027'.
rfq_idNoOwn reference number. Default RFQ-YYYYMMDD-01.
criteriaNoEvaluation criteria with weights (any scale, normalised to 100).
due_dateNoSubmission deadline, YYYY-MM-DD. Default issue date plus 14 days.
languageNoLanguage of the answer. Default de.
timelineNo
issue_dateNoYYYY-MM-DD. Default today.
deliverablesNo
requirementsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly, idempotent, closed-world, non-destructive) by disclosing that the tool is deterministic with no AI, stores nothing, and returns full ready-to-paste text plus a template link. It also spells out the access model — an AICTIONBOT licence is required, with one free check per connection every 30 days via 'Connect without a licence'. No contradiction with readOnlyHint.

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 dense and useful, but it arrives as one very long serial sentence with a brand prefix ('KULIC Advisory, AICTIONBOT™ Workbench.') ahead of the verb, so the payload is not front-loaded. The six-section enumeration earns its place; the branding and some boilerplate do not.

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?

For a 13-parameter, nested-object tool with no output schema, the description is close to self-sufficient: it defines the artifact structure, defaults, return shape, and licensing. The gaps are minor — the deliverables and requirements parameters and the timeline sub-fields are never mentioned, so an agent still has to read the schema for those.

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?

At 62% schema coverage the description carries real weight and does so: it documents defaults the schema does not (issue date today, due date issue+14d, rfq_id RFQ-YYYYMMDD-01, language de), explains criteria weights are normalised to 100 with a suggested price/quality/delivery/service/terms split, and describes the line fields. A few parameters (deliverables, requirements, timeline sub-fields) remain undocumented in both places.

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 — 'Drafts a complete request for quotation in German or English following the Execution Toolkit template T10' — and enumerates the six sections the artifact contains. An agent can tell this apart from create_nda or write_scope_of_work purely from the RFQ template designation 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies the use case clearly (producing a buyer-side RFQ) and adds a concrete handoff rule: the returned Excel template T10 link is what fill_template consumes. It also sets an authoring policy — missing details become bracketed placeholders, never invented. No explicit when-not-to-use or named sibling alternative is given, which keeps it out of 5 territory.

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.