Skip to main content
Glama

AICTIONBOT™ Werkbank

Write minutes and commitments from notes of a supplier meeting (AICTIONBOT™ minutes)

write_meeting_minutes
Read-only

Uses one AI analysis of the licence. Turns notes or a transcript of a procurement conversation (for example with a supplier) into minutes for the buyer: summary, decisions, commitments with who, what and by when, open points, risks and a short follow-up email to the other party. Only what was said; no invented decisions, numbers or dates. The notes are processed for this answer only and are not stored by KULIC Advisory.

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": {
      "notes": "<notes>"
    },
    "name": "write_meeting_minutes"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesYesNotes or transcript of the conversation.
languageNoLanguage of the answer: de, en, fr, es, pt or zh. Default de.
meeting_typeNoOptional: type of conversation, e.g. 'annual price negotiation with packaging supplier'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / language / enum
      Previous value: -[
      -  "en",
      -  "de",
      -  "fr",
      -  "es",
      -  "pt",
      -  "zh"
      -]New value: +[
      +  "en",
      +  "de",
      +  "fr",
      +  "es",
      +  "pt",
      +  "zh",
      +  "hr",
      +  "sr"
      +]
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, non-idempotent and non-destructive, so the safety profile is covered. The description still adds meaningful context beyond them: one licence-consuming AI analysis per call, a fidelity constraint ('Only what was said; no invented decisions, numbers or dates'), and a data-handling promise that notes are processed for this answer only and not stored. It stops short of describing output length or what happens with very long or non-conforming input.

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?

The structure is excellent: purpose first, then the concrete deliverables, then constraints, then the data-handling note, so an agent can stop reading once it has what it needs. The opening clause 'Uses one AI analysis of the licence' is slightly awkward and reads as commercial framing rather than functional information, but nothing else is padding.

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?

There is no output schema, so the description carries the burden of explaining the return value — and it does, by listing the sections produced. Licence consumption and the no-storage guarantee round out the picture for a single-shot generative tool. Minor gaps remain around output length and behaviour with edge-case inputs, which keeps it below a 5.

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 all three parameters — notes, language and meeting_type — are already documented in structured data. The description adds a little framing by saying the input is notes or a transcript and that the follow-up email is addressed to the other party, but it adds no format, length, or language-selection guidance beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

The description gives a specific verb and resource ('Turns notes or a transcript of a procurement conversation into minutes for the buyer') and enumerates the produced sections: summary, decisions, commitments with who/what/by when, open points, risks, and a follow-up email. That is far more informative than the title alone. It does not, however, explicitly separate itself from nearby authoring siblings such as write_scope_of_work or write_buying_policy, so an agent must infer the boundary from the domain word 'meeting minutes'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied by the input requirement: it applies to notes or a transcript of a procurement/supplier conversation, with an example given in the schema for meeting_type. There is no statement of when NOT to use it, no prerequisites (minimum note length is left to the schema), and no alternative named for related jobs like scope-of-work or buying-policy drafting.

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.