Skip to main content
Glama

AICTIONBOT™ Werkbank

Practise the negotiation: plays the supplier, answers the buyer's last message and coaches it (AICTIONBOT™ negotiation sparring)

negotiation_round
Read-only

Needs the user's AICTIONBOT™ Werkbank licence. Rounds do not use the licence quota; they are limited to 30 per hour. Role play, one round per call: pass the situation and the transcript so far, ending with the buyer's latest message. Returns the supplier's reply in role, a rating of the buyer's last message (strong, ok or weak) with one concrete tip, and the current state of the deal. The supplier is a fictional sales person; no facts about real companies are invented. Show the supplier's reply to the user, let the user answer in their own words, and call again with the extended transcript. Nothing is stored by KULIC Advisory; the transcript lives in the conversation.

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": {
      "what_is_bought": "<what_is_bought>",
      "transcript": "<transcript>"
    },
    "name": "negotiation_round"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNoOptional: what the buyer wants to reach.
languageNoLanguage of the answer: de, en, fr, es, pt or zh. Default de.
supplierNoOptional: type of supplier.
walk_awayNoOptional: the point at which the buyer walks away.
transcriptYesThe conversation so far, oldest first. The last entry must be the buyer's latest message.
supplier_styleNoHow the supplier negotiates: friendly but firm, tough and confident, or evasive. Default tough.
what_is_boughtYesWhat the negotiation is about. Keep it the same in every round.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations it discloses a licence prerequisite, that rounds do not consume quota, a hard limit of 30 rounds per hour, and that nothing is stored server-side with the transcript living in the conversation. It also flags that the supplier is fictional and invents no facts about real companies. These are exactly the auth, rate-limit and side-effect details an agent cannot get from readOnlyHint/destructiveHint alone, and nothing conflicts with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences, front-loaded with the prerequisite and limits before the operating loop and return values. No filler, no repetition of the title's marketing phrasing, and each sentence adds distinct information for the caller.

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?

There is no output schema, and the description compensates fully by naming the three return elements: the in-role supplier reply, the strong/ok/weak rating with one concrete tip, and the current deal state. Combined with the stated round limit and storage posture, an agent has everything needed to call it correctly and loop it.

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 goal, language, supplier, supplier_style, walk_away and transcript are already documented in the schema itself. The description's added meaning is limited to reinforcing that the transcript ends with the buyer's latest message and that what_is_bought should stay constant across rounds, both of which the schema descriptions already state. Baseline 3 is appropriate.

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 states a specific verb and resource: role-play one negotiation round per call, returning the supplier's in-role reply, a rating of the buyer's last message, and deal state. This is concrete and distinguishable from a generic chat tool. It does not, however, contrast itself with siblings such as plan_negotiation or evaluate_negotiation, so the agent must infer the boundary.

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 gives a clear operating loop: pass situation plus transcript ending with the buyer's latest message, show the reply to the user, let them answer in their own words, then call again with the extended transcript. That covers when to call and how to sequence calls. It stops short of explicit exclusions or naming which sibling to use for planning or post-hoc scoring instead.

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.