justicelibre

get_decision_text

Read-only

Extraction du texte intégral d'une décision relevant de l'ordre administratif (Conseil d'État, TA, CAA).

Identifiants acceptés :
- `DCE_XXX_YYYYMMDD` (CE), `DTA_XXX_YYYYMMDD` (TA),
  `DCAA_XXX_YYYYMMDD` (CAA) — extraction depuis le bulk JADE local.
- `CETATEXT…` (id Légifrance/CETA renvoyé par `search_admin`) — lookup
  direct dans le bulk JADE local, texte intégral inclus.
- `/Ariane_Web/AW_DCE/|XXXXXX` (ou abrégé `|XXXXXX`) — récupération EN
  DIRECT du texte intégral via le plugin Sinequa du Conseil d'État.
  Fonctionne pour toute décision ArianeWeb, y compris hors bulk JADE.

INCOMPATIBILITÉS MAJEURES :
- Identifiants JURITEXT — rediriger vers `get_decision_judiciaire_libre`
  ou `get_decision_judiciaire`.
- Identifiants CELEX `6XXXXCJXXXX` — rediriger vers `get_decision_cjue`.
- Identifiants HUDOC `001-XXXXXX` — rediriger vers `get_decision_cedh`.

Args:
    decision_id: identifiant de la décision (avec ou sans suffixe .xml)

Returns:
    Dict comportant les métadonnées complètes, `texte_integral` (booléen :
    ⚠️ quand il vaut false, `full_text` n'est QUE le sommaire du Centre de
    documentation — 68 % des décisions administratives d'avant 1990 n'ont
    pas de texte dans la source ouverte ; `note_texte` le dit en clair ;
    ne jamais citer ce champ comme un extrait de la décision) et `full_text` (texte
    intégral). Si la décision est introuvable, dict d'erreur structuré
    `{error, error_category: "not_found", retryable}` avec les tools
    alternatifs à essayer.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	No
`decision_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 17, 2026
- addedInput schema / properties / decision_id / default
```
Added value: +""
```
- addedInput schema / properties / id
```
Added value: +{
+  "default": "",
+  "title": "Id",
+  "type": "string"
+}
```
- removedInput schema / required
```
Removed value: -[
-  "decision_id"
-]
```

Changed4 schema fields changedJul 19, 2026

addedOutput schema / additionalProperties
```
Added value: +true
```

removedOutput schema / properties

Removed value: -{
-  "result": {
-    "anyOf": [
-      {
-        "additionalProperties": true,
-        "type": "object"
-      },
-      {
-        "type": "null"
-      }
-    ],
-    "title": "Result"
-  }
-}

removedOutput schema / required
```
Removed value: -[
-  "result"
-]
```

changedOutput schema / title

Previous value: -"get_decision_textOutput"New value: +"get_decision_textDictOutput"

AddedMay 22, 2026
RemovedMay 22, 2026
First observedApr 16, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description discloses a critical caveat not visible in annotations: when texte_integral is false, full_text is only the summary, and warns never to cite it as an extract. It also documents the structured not_found error dict and alternative tools. The readOnlyHint annotation is consistent with 'extraction', so there is no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but tightly structured: purpose, accepted identifiers, incompatibilities, args, returns. It is front-loaded with the core purpose, and every section carries necessary operational detail rather than filler.

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 a complex lookup tool, the description covers identifier variants, incompatibility routing, return semantics, a data-availability caveat, and the error contract. The only notable gap is the undocumented id parameter in the input schema; otherwise an agent has enough context to invoke the tool correctly.

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?

With 0% schema coverage, the description must document the parameters. It richly explains decision_id's accepted formats (DCE_..., DTA_..., DCAA_..., CETATEXT..., ArianeWeb) and the .xml suffix tolerance, but it never mentions the schema's other parameter, id. An agent may be uncertain whether id is an alias, a deprecated field, or a separate identifier.

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 opens with a specific verb and resource: 'Extraction du texte intégral d'une décision relevant de l'ordre administratif (Conseil d'État, TA, CAA)'. It clearly distinguishes accepted identifier types and explicitly routes incompatible identifiers to sibling tools, so the tool's role is unambiguous.

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?

A dedicated 'Identifiants acceptés' section enumerates valid inputs, and 'INCOMPATIBILITÉS MAJEURES' states exactly when to use get_decision_judiciaire_libre/get_decision_judiciaire, get_decision_cjue, or get_decision_cedh. This is explicit when-to-use/when-not-to-use guidance.

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

All justicelibre tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.