Skip to main content
Glama

AICTIONBOT™ Werkbank

Check an action log or implementation tracker: overdue, blocked, no owner, no due date, duplicates, overload, traffic light per work package

check_actions
Read-onlyIdempotent

AICTIONBOT™ action check by KULIC Advisory, built on the Execution Toolkit templates T07 (cross-functional action log) and T06 (implementation tracker). Takes the user's list of actions or tasks and returns a ready status report: done rate, overdue items sorted by days, blocked items, open items on the critical path, items due soon, items without an owner or due date, probable duplicates, people with more open items than the limit, and a red, yellow or green light per work package with progress. Per item: action, owner, due date, status (open, in progress, done, blocked), work package or workstream, progress in percent, critical path (yes/no). German or English column names are recognised (Maßnahme, Aufgabe, Verantwortlich, Termin, Status, Arbeitspaket, Fortschritt, kritischer Pfad). 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": {
      "items": "<items>"
    },
    "name": "check_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoReference date, YYYY-MM-DD. Default today.
itemsYesAction rows: action, owner, due (date), status, workstream, progress (percent), critical (yes/no).
languageNoLanguage of the answer. Default de.
soon_daysNoDays ahead that count as due soon. Default 7.
max_open_per_personNoOpen items per person above which overload is flagged. Default 8.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses that processing is deterministic, that nothing is stored, and the exact auth/licence model including the free-tier limit. It also implicitly bounds the workload via the per-item field list, giving the agent behavioural context the annotations cannot carry.

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 mostly front-loaded, but it is delivered as one long run-on paragraph with no breaks, and it opens with branding boilerplate ("AICTIONBOT™ ... by KULIC Advisory", trademark symbols) that an agent gains nothing from. The output enumeration and licence clause are both long and could be tightened, though most clauses do carry information.

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?

For a complex analytical tool with no output schema, the description fully specifies what comes back (both aggregate metrics and the per-item fields) plus auth requirements and language behaviour. Nothing an agent needs in order to call it correctly or set expectations is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is nominally 100%, but the `items` array is typed only as generic objects with no nested properties — the description is the sole source defining the row fields (action, owner, due date, status with its four values, work package, progress %, critical path) and it also documents German column aliases (Maßnahme, Verantwortlich, Termin, Arbeitspaket, Fortschritt, kritischer Pfad). It additionally ties soon_days and max_open_per_person to the concepts "due soon" and overload.

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 concrete verb and resource ("action check" on a user-supplied list of actions/tasks) and pins the domain to action logs (T07) and implementation trackers (T06), which separates it from siblings like check_approval_matrix, check_rasci_matrix or check_kpis. The enumerated output list (done rate, overdue, blocked, duplicates, overload, traffic light per work package) makes the tool's function unmistakable.

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 clearly establishes the input context — the user hands over a list of actions/tasks and gets a status report back — and states prerequisites (licence/sign-in, free single check per 30 days). It never names an alternative sibling or an explicit when-not condition, so it stops short of full routing guidance.

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.