Skip to main content
Glama

AICTIONBOT™ Werkbank

Check a RASCI matrix against the people list: tasks without an A, several A, no R, roles without an active person

check_rasci_matrix
Read-onlyIdempotent

AICTIONBOT™ RASCI Checker by KULIC Advisory. Checks a RASCI matrix (tasks by roles or people, codes R, A, S, C, I, also A/R) against an optional people list (role, status, leaving date, absence). Returns the tasks that need action: no accountable role, several A, no R, too many R or C, and roles or people that hold an A or R but left, are absent or are unknown. 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": {
      "tasks": "<tasks>"
    },
    "name": "check_rasci_matrix"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoReference date, YYYY-MM-DD. Default today.
tasksYesOne object per task: task (name), process (optional), assignments (object: role or person name -> code such as R, A, A/R, S, C, I). Instead of assignments the role names may be given as further keys of the task object.
peopleNoOptional people list: person, role, status (active, left, absent), left_on (YYYY-MM-DD), absent_until (YYYY-MM-DD).
languageNoLanguage of the answer. Default de.

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?

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, and the description goes well beyond them: deterministic with no AI, nothing stored, sign-in required, and a concrete free-tier limit of one check per connection every 30 days. That is exactly the licensing and rate-limit context an agent needs before invoking a licensed tool.

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 core content is front-loaded and dense, but the opening brand line ("AICTIONBOT™ RASCI Checker by KULIC Advisory") is marketing that does not help tool selection, and the licensing sentence is long. Still, no sentence repeats what annotations or schema already state.

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 four parameters, no output schema and a nested-free payload, the description covers inputs, the exact return content (which tasks need action and why) and the access model, so an agent can call it correctly. Minor gaps remain around what a passing matrix returns and how findings are ordered, but nothing essential to invocation is missing.

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 required/optional status, the YYYY-MM-DD pattern, item limits and the assignments map are all already documented. The description adds only the RASCI code vocabulary (R, A, S, C, I, A/R) and the role-vs-person framing, and says nothing extra about as_of or language beyond the schema.

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?

The description names a specific verb and resource ("Checks a RASCI matrix") and enumerates the exact problem classes it reports: no accountable role, several A, no R, too many R or C, and dangling/absent/unknown holders. That is specific enough for an agent to distinguish it from check_approval_matrix or check_actions without opening a 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?

Usage context is clear: it runs against tasks and an optional people list, and the people-list clause tells the agent when the extra parameter buys more findings (left, absent, unknown role holders). It never names an alternative tool or an explicit when-not-to-use case, so it stops short of a 5.

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.