eu-ai-act-mcp

EU AI Act FAQ

euaiact_answer_question

Read-onlyIdempotent

Answer EU AI Act questions by searching FAQs. Get best-match answers with article references, covering classification, deadlines, roles, and penalties.

Instructions

Search frequently asked questions about the EU AI Act and get best-match answers with article references. Covers classification, deadlines, roles, governance, documentation, risk assessment, penalties, GPAI systemic risk, FRIA, transparency, and sector-specific guidance.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`question`	Yes	User question about the EU AI Act

Output Schema

TableJSON Schema

Name	Required	Description
`answer`	Yes
`question`	Yes
`confidence`	Yes
`match_status`	Yes	Whether a FAQ answer was accepted. A candidate below the threshold is not a match.
`matched_question`	No
`article_references`	Yes
`candidate_question`	No	Unaccepted closest candidate on abstention, for query refinement only.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.7.0Oct 2, 2026

addedOutput schema / properties / candidate_question

Added value: +{
+  "description": "Unaccepted closest candidate on abstention, for query refinement only.",
+  "type": "string"
+}

removedOutput schema / properties / lexbeam_url
```
Removed value: -{
-  "type": "string"
-}
```

addedOutput schema / properties / match_status

Added value: +{
+  "description": "Whether a FAQ answer was accepted. A candidate below the threshold is not a match.",
+  "enum": [
+    "matched",
+    "no_match"
+  ],
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "question",
-  "answer",
-  "confidence",
-  "article_references"
-]New value: +[
+  "question",
+  "match_status",
+  "answer",
+  "confidence",
+  "article_references"
+]

Changed1 schema field changedv1.5.0Aug 19, 2026
- addedOutput schema / properties / matched_question
```
Added value: +{
+  "type": "string"
+}
```
First observedv1.1.5Jun 14, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so safety and determinism are covered. The description adds that responses are best-match with article references, which is mild but useful output-shaped context. It doesn't disclose matching behavior, ranking, or what happens with unmatched questions.

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?

Two sentences, with the core action front-loaded before the topic list. The coverage enumeration is long but earns its place by signalling routing scope. Slightly list-heavy but no wasted framing.

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 an output schema present, the description need not explain return values, and it correctly restricts itself to scope. Topic coverage plus the FAQ-vs-article distinction is enough for an agent to call it correctly; only explicit sibling routing 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?

There is a single parameter with 100% schema description coverage ('User question about the EU AI Act'), so the schema carries the semantics. The description adds nothing about phrasing, length, or language of the question. Baseline 3 is appropriate when the schema fully documents the lone parameter.

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 specific verb and resource ('Search frequently asked questions about the EU AI Act') plus the return shape ('best-match answers with article references'). The FAQ-search scope cleanly separates it from siblings like euaiact_get_article or euaiact_assess_system, which retrieve article text or run assessments rather than answering questions.

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?

The topic enumeration (classification, deadlines, documentation, penalties, GPAI, FRIA, etc.) implicitly tells the agent when this tool applies, but no explicit when-to-use rule or alternative is named. It does not say, e.g., to prefer this over get_article for quick answers. Usage is implied rather than directed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server