Skip to main content
Glama

AICTIONBOT™ Werkbank

Role profile and job advertisement for a procurement role: responsibilities along the source-to-pay chain, RACI rows, KPIs, skills, segregation-of-duties check

describe_role
Read-onlyIdempotent

AICTIONBOT™ role profile by KULIC Advisory (tool 38), built on the Execution Toolkit templates T03 (process taxonomy with RASCI), T16 (competency assessment) and T18 (capability matrix). Takes the role name, level (operativ, strategisch, fuehrung, leitung), categories, approval limit in euros, who it reports to, and activities with a RACI letter each (R does, A is accountable, C is consulted, I is informed). Activities may be named in the user's own words or by number from the KULIC five-stage chain (1 strategy and categories, 2 sourcing and supplier selection, 3 contracts and supplier management, 4 ordering and goods receipt, 5 invoice, payment, master data; 30 activities, for example 2.5 negotiate, 4.3 approve purchase orders, 5.4 release payments). Returns purpose, RACI rows by stage, KPIs, skills, approval rule, segregation-of-duties conflicts (red, amber) and a job advertisement in German and English with a placeholder for what the employer offers. 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

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": {
      "activities": "<activities>"
    },
    "name": "describe_role"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoRole name or job title, e.g. Strategic buyer packaging.
levelNoLevel: operativ (operational), strategisch (strategic), fuehrung (team lead), leitung (head of procurement).
languageNoLanguage of the answer. Default de. The job advertisement always comes in German and English.
activitiesYesRows: activity (own words or chain number such as 2.5) and raci (R, A, C or I).
categoriesNoCategories the role buys, e.g. packaging and logistics.
reports_toNoWho the role reports to.
approval_limitNoApproval limit per order in euros.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the read-only, idempotent, non-destructive, closed-world profile, and the description adds real context on top: deterministic, no AI, nothing stored, and an explicit auth model with a licence and a free 30-day check per connection. It also enumerates what is returned, so the agent knows the shape of the output despite there being no output schema.

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 is front-loaded only after a branding sentence containing trademark symbols and template codes T03/T16/T18 that an agent cannot use. The rest is dense but earns its place; the opening sentence is noise that should have been trimmed.

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 7-parameter generation tool with no output schema, the description covers inputs, the enumerated return values, and the auth constraints. Only edge behavior such as how the 80-activity cap or conflicting RACI rows are handled is left unstated.

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?

Schema coverage is 100%, so the baseline would be 3, but the description adds meaning the schema lacks: it explains each RACI letter (R does, A accountable, C consulted, I informed) and expands the activity input with the five-stage KULIC chain and named examples such as 2.5 negotiate and 5.4 release payments. That is genuine disambiguation for the required parameter.

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 concrete verb and resource: it builds a procurement role profile from activities/RACI rows and returns purpose, RACI rows by stage, KPIs, skills, approval rule, SoD conflicts and a bilingual job advertisement. It is clearly distinguishable from a plain matrix checker, though it never names a sibling to contrast with and the opening branding sentence delays the actual purpose.

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 inventory (supply role, level, categories, activities with RACI letters) rather than stated as when-to-use guidance. There is no indication of when to prefer this over check_rasci_matrix or assess_team, and no statement of prerequisites beyond the licence note.

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.