Diplomètre

Comparer des formations

comparer_formations

Read-onlyIdempotent

Vous hésitez entre plusieurs formations ? Comparez de 2 à 4 formations côte à côte pour choisir vos études : est-ce difficile d’y entrer, combien ça coûte, est-ce que ça mène à un emploi ? Diplomètre présente l’accès, la réussite, la poursuite d’études, l’emploi, le salaire, les frais et la reconnaissance du diplôme, dans votre ordre, sans classement ni note globale. Chaque chiffre donne son producteur, son année et sa fiabilité, ou « non communiqué ». Le taux d’accès ne prédit pas votre admission. La réponse se termine par « Voir cette comparaison sur Diplomètre », un lien vers le comparateur avec les formations retenues.

Input Schema

Name	Required	Description	Default
`identifiants`	Yes	De 2 à 4 identifiants de formations, dans l’ordre voulu

Output Schema

Name	Required	Description	Default
`lecture`	No
`rappels`	No
`formations`	Yes
`comparaison`	No
`introuvables`	No
`avertissements`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026

changedOutput schema / properties / formations / items / properties / chiffres / items / oneOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "etat": {
-        "const": "disponible",
-        "type": "string"
-      },
-      "indicateur": {
-        "type": "string"
-      },
-      "notes": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "precision": {
-        "type": "string"
-      },
-      "question": {
-        "type": "string"
-      },
-      "source": {
-        "anyOf": [
-          {
-            "additionalProperties": false,
-            "properties": {
-              "annee": {
-                "type": [
-                  "string",
-                  "null"
-                ]
-              },
-              "fiabilite": {
-                "type": [
-                  "string",
-                  "null"
-                ]
-              },
-              "licence": {
-                "type": "string"
-              },
-              "producteur": {
-                "type": "string"
-              }
-            },
-            "required": [
-              "producteur",
-              "annee",
-              "fiabilite"
-            ],
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "unite": {
-        "type": "string"
-      },
-      "valeur": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "indicateur",
-      "question",
-      "etat",
-      "valeur",
-      "source"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "etat": {
-        "const": "non communiqué",
-        "type": "string"
-      },
-      "indicateur": {
-        "type": "string"
-      },
-      "motif": {
-        "type": "string"
-      },
-      "question": {
-        "type": "string"
-      },
-      "source": {
-        "type": "null"
-      },
-      "valeur": {
-        "type": "null"
-      }
-    },
-    "required": [
-      "indicateur",
-      "question",
-      "etat",
-      "valeur",
-      "source"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "etat": {
+        "const": "disponible",
+        "type": "string"
+      },
+      "indicateur": {
+        "type": "string"
+      },
+      "notes": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "precision": {
+        "type": "string"
+      },
+      "question": {
+        "type": "string"
+      },
+      "source": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "annee": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "fiabilite": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "licence": {
+                "type": "string"
+              },
+              "producteur": {
+                "type": "string"
+              },
+              "reference": {
+                "type": "string"
+              },
+              "validite": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "producteur",
+              "annee",
+              "fiabilite"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "unite": {
+        "type": "string"
+      },
+      "valeur": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "indicateur",
+      "question",
+      "etat",
+      "valeur",
+      "source"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "etat": {
+        "const": "non communiqué",
+        "type": "string"
+      },
+      "indicateur": {
+        "type": "string"
+      },
+      "motif": {
+        "type": "string"
+      },
+      "question": {
+        "type": "string"
+      },
+      "source": {
+        "type": "null"
+      },
+      "valeur": {
+        "type": "null"
+      }
+    },
+    "required": [
+      "indicateur",
+      "question",
+      "etat",
+      "valeur",
+      "source"
+    ],
+    "type": "object"
+  }
+]

First observedOct 12, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses that no ranking or global score is produced, that every figure carries producer/year/reliability or 'non communiqué', that the taux d’accès is not a prediction of admission, and that the response ends with a Diplomètre link. That is substantive behavioral and output-shape context.

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?

Purpose and scope are front-loaded in the first sentence, and the rest is packed with relevant caveats. It runs long with several subordinate clauses, but nearly every sentence carries a distinct constraint (no ranking, provenance, non-prediction, footer link), so little is wasted.

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?

An output schema exists, yet the description still usefully characterizes the content and the trailing link without over-specifying the return format. Combined with full schema coverage and annotations, an agent has everything needed to call this 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?

Schema description coverage is 100%, so the identifiants field, its 2–4 bounds, and the id-format rules are already fully documented in the schema. The description's 'dans votre ordre' merely echoes the schema's 'dans l’ordre voulu', adding no new syntax or format guidance.

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 precise verb and resource ('Comparez de 2 à 4 formations côte à côte') and enumerates exactly what dimensions are compared (accès, réussite, poursuite d’études, emploi, salaire, frais, reconnaissance). It also fixes its scope against siblings by specifying 'sans classement ni note globale', so an agent can tell it apart from lire_formation or rechercher_formations.

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?

The opening 'Vous hésitez entre plusieurs formations ?' gives a clear situational trigger and the body constrains the count to 2–4. However, it never names an alternative tool for the single-formation case (lire_formation) or the search case (rechercher_formations), so routing is implied rather than explicit.

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

All Diplomètre 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.

Resources

Need Help?