Skip to main content
Glama

AICTIONBOT™ Werkbank

Automation portfolio with benefit calculation: hours and euros per year per use case, payback and a phase plan, from your own figures

automation_portfolio
Read-onlyIdempotent

Takes a list of automation or AI use cases with cases per year, minutes per case before and after, the implementation effort in days and whether the case needs AI. Returns per use case the hours and euros saved per year, the one-off cost and the payback in months, sorted into phase 1 (pays off within 6 months), phase 2 (7 to 18 months) and phase 3 (more than 18 months, put on hold), the cases that save no time, the cases that already work without AI, the totals and the next step. Uses your hourly rate and day rate; without them it assumes 45 euros per hour and 800 euros per implementation day and says so. The result is an estimate from your figures, not a promise. For a single process step use process_lever, to rate one AI use case use check_ai_use_case. Licence, or one free check every 30 days.

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": {
      "rows": "<rows>"
    },
    "name": "automation_portfolio"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesOne row per use case: use_case, volume (cases per year), minutes_before, minutes_after, effort_days, ai (yes or no). German column names work too (anwendungsfall, vorgaenge, minuten_vorher, minuten_nachher, aufwand, ki).
languageNoLanguage of the answer. Default de.
day_rate_eurNoOptional: cost per implementation day in euros. Default 800.
hourly_rate_eurNoOptional: internal cost per hour in euros. Default 45.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description adds real context beyond that with default rates (45 EUR/hour, 800 EUR/day) and the fact that defaults are disclosed in the answer. It also sets expectations that the result is an estimate from the user's figures, not a promise, and mentions the 30-day free-check limit. However, it says nothing about runtime, size limits or failure modes for large row sets (up to 5000), leaving a gap for a batch computation.

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?

Front-loaded: what it takes, what it returns, then alternatives, then caveats. Every clause carries information — output breakdown, phase thresholds, defaults, licence. The single dense paragraph with run-on sentences makes the phase thresholds and the caveats harder to scan than they should be, so not a 5.

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?

No output schema exists, so the description must carry the return contract, and it does: per-use-case saved hours and euros, one-off cost, payback in months, phase bucketing with explicit thresholds, edge cases (no time saved, already works without AI), totals and next step. For a computational tool with a fully documented schema and clear safety annotations, nothing an agent needs in order to call it correctly is missing.

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 is 3, and the description does slightly more by explaining that rates are the user's own hourly/day rates and what happens when they are omitted. It also frames what the row fields mean economically (minutes before/after → hours and euros saved per year, effort in days → one-off cost and payback). Marginal added value over the schema, which already documents each field and its default.

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 ('Takes a list of automation or AI use cases... Returns per use case the hours and euros saved per year') with the exact computation inputs and outputs, and names the two siblings it is not (process_lever, check_ai_use_case). An agent can distinguish it from a single-case rater or a single-step lever without opening the schema.

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

Usage Guidelines5/5

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

Explicitly routes the agent: 'For a single process step use process_lever, to rate one AI use case use check_ai_use_case' — both an alternative and the condition selecting it. It also discloses a usage constraint (licence, one free check every 30 days), which is the kind of when-to-use information agents need.

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.