Skip to main content
Glama

Aidoptio: AI adoption catalog, estimates and advisor tools

AI literacy scan (EU AI Act, Article 4)

ai_literacy_scan
Read-onlyIdempotent

For an organisation that wants to show what it does about AI literacy under Article 4 of Regulation (EU) 2024/1689. Give the role groups and, optionally, your own yes/partly/no answers per checklist question and the questions you have evidence on file for. Returns a status per step (the four steps of the European Commission Q&A plus being able to show it): unknown, open, partly or measures_reported; the evidence expected per question; the gaps in the file; the actions with priority; and related obligations that are not Article 4 (Articles 26, 27, 50 and 5). No score and no percentage: Article 4 asks for measures, not for a level. Without answers it returns the full checklist. Same rule set as the section on aidoptio.com. Statuses are based only on your own answers: an aid, not legal advice and not proof of meeting the AI Act. Deterministic: no model is called and the answers are not stored.

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": {
      "roles": "<roles>"
    },
    "name": "ai_literacy_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the returned text: en (English, default) or nl (Dutch).en
rolesYesRole groups that work with AI: office, management, hr-sales, board.
ai_usesNoHow AI is used. recruitment-or-hr and credit-or-eligibility make the high-risk questions 4.1 to 4.6 a point to check.
answersNoYour own answer per checklist question id, e.g. {"1.1": "yes", "2.4": "partly"}. Call the tool without answers to get the ids and the questions.
is_providerNotrue = provider, false = deployer, left out = not established yet.
acts_on_its_ownNotrue when an AI system acts on its own, for example an agent that sends emails.
evidence_on_fileNoIds of the questions you have evidence on file for. Leave out to skip the file check (dossier_gaps is then null).
high_risk_confirmedNotrue when you have established that the recruitment, HR or credit use is high-risk (Annex III, point 4 or 5). Then questions 4.1 to 4.6 get priority.

Output Schema

NameRequiredDescriptionDefault
lawYes
urlYes
modeYes
toolNo
stepsYes
articleNo
disclaimerYes
dossier_gapsYes
tool_versionNo
first_actionsYes
not_article_4No
self_reportedYes
demonstrabilityYes
related_obligationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only say read-only/idempotent/non-destructive/closed-world; the description goes well beyond that by disclosing that the result is deterministic with no model call, that answers are not stored, that statuses derive solely from the user's own answers, and that it is not legal advice or proof of compliance. It also enumerates the possible status values and explains why no score or percentage is produced, which heads off a very likely agent misreading.

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 is front-loaded (audience, inputs, returns) and nearly every clause carries information, including the useful no-score justification and the disclaimer. It is dense and semicolon-chained, and 'Same rule set as the section on aidoptio.com' adds little for an agent deciding how to call it.

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 an 8-parameter tool with nested objects and an output schema, the description covers what comes back (statuses, expected evidence, dossier gaps, prioritised actions, related obligations) and the key trust properties (deterministic, stateless, not legal advice). Minor gaps remain: `lang` and the provider/deployer and high-risk flags are only explained in the schema; the output schema does absorb return-value detail.

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 the baseline is 3 and the schema already explains roles, answers, evidence_on_file, is_provider, acts_on_its_own and high_risk_confirmed in more detail than the description does. The description adds only the behavioural note that omitting answers returns the full checklist, and the rationale that Article 4 wants measures rather than a level.

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 opening names the exact obligation being served (AI literacy under Article 4 of Regulation (EU) 2024/1689) and the tool's output shape (status per step, gaps, prioritised actions, related non-Article-4 obligations), so an agent can tell this apart from triage/readiness siblings. The weakness is that the action verb is framed indirectly ('For an organisation that wants to show...') rather than as 'assess/scan X given Y'.

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?

There is a clear intended audience and a genuine in-tool sequencing hint -- 'Without answers it returns the full checklist' and the schema note to call without answers first to get question ids. However, no alternative sibling (ai_act_triage, benchmark_readiness, verify_report) is named or ruled in/out, so cross-tool selection is left to inference.

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.

Resources