Skip to main content
Glama

Compare two models

comparer_modeles
Read-onlyIdempotent

Side-by-side scores and prices of two models of the same category, the better one for each buyer profile, and the Picksly comparison page.

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": {
      "categorie": "<categorie>",
      "modele_a": "<modele_a>",
      "modele_b": "<modele_b>"
    },
    "name": "comparer_modeles"
  }
}

Input Schema

NameRequiredDescriptionDefault
paysNoISO country code of the buyer (FR, US, GB, DE, ES, IT, NL, BE, PT, and most others mapped to the nearest store). Default FR.
langueNoLanguage of the Picksly page links. Default: the page decides.
modele_aYes
modele_bYes
categorieYesProduct category page: telephones = smartphones, tablettes = tablets, ordinateurs-portables = laptops, montres-connectees = smartwatches, montres-sport = sport watches.

Output Schema

NameRequiredDescriptionDefault
aYes
bYes
deviseYes
marcheYes
mentionYesAffiliate disclosure.
categorieYes
comparaisonYesPicksly page comparing the two models.
meilleur_par_profilYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "a": {
      +      "properties": {
      +        "annee": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "criteres": {
      +          "additionalProperties": {
      +            "type": "number"
      +          },
      +          "description": "Per-criterion scores 0–100 (performance, battery…).",
      +          "type": "object"
      +        },
      +        "fiche": {
      +          "description": "Picksly page of the model, explaining how its scores are calculated.",
      +          "type": "string"
      +        },
      +        "marque": {
      +          "type": "string"
      +        },
      +        "modele": {
      +          "type": "string"
      +        },
      +        "notes": {
      +          "properties": {
      +            "budget": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "globale": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "premium": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "smart": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            }
      +          },
      +          "required": [
      +            "globale",
      +            "budget",
      +            "smart",
      +            "premium"
      +          ],
      +          "type": "object"
      +        },
      +        "offres": {
      +          "items": {
      +            "properties": {
      +              "devise": {
      +                "type": "string"
      +              },
      +              "etat": {
      +                "description": "neuf = new, reconditionne = refurbished.",
      +                "enum": [
      +                  "neuf",
      +                  "reconditionne"
      +                ],
      +                "type": "string"
      +              },
      +              "lien_achat": {
      +                "description": "Affiliate link to the store page, through picksly.fr.",
      +                "type": "string"
      +              },
      +              "marchand": {
      +                "description": "Store selling the offer.",
      +                "type": "string"
      +              },
      +              "prix": {
      +                "type": "number"
      +              },
      +              "prix_releve_le": {
      +                "description": "Date (YYYY-MM-DD) the price was last read at the store.",
      +                "type": [
      +                  "string",
      +                  "null"
      +                ]
      +              }
      +            },
      +            "required": [
      +              "etat",
      +              "prix",
      +              "devise",
      +              "marchand",
      +              "prix_releve_le",
      +              "lien_achat"
      +            ],
      +            "type": "object"
      +          },
      +          "type": "array"
      +        },
      +        "remarque": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "marque",
      +        "modele",
      +        "annee",
      +        "notes",
      +        "criteres",
      +        "offres",
      +        "fiche"
      +      ],
      +      "type": "object"
      +    },
      +    "b": {
      +      "properties": {
      +        "annee": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "criteres": {
      +          "additionalProperties": {
      +            "type": "number"
      +          },
      +          "description": "Per-criterion scores 0–100 (performance, battery…).",
      +          "type": "object"
      +        },
      +        "fiche": {
      +          "description": "Picksly page of the model, explaining how its scores are calculated.",
      +          "type": "string"
      +        },
      +        "marque": {
      +          "type": "string"
      +        },
      +        "modele": {
      +          "type": "string"
      +        },
      +        "notes": {
      +          "properties": {
      +            "budget": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "globale": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "premium": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "smart": {
      +              "description": "Score 0–100, null when not enough is measured.",
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            }
      +          },
      +          "required": [
      +            "globale",
      +            "budget",
      +            "smart",
      +            "premium"
      +          ],
      +          "type": "object"
      +        },
      +        "offres": {
      +          "items": {
      +            "properties": {
      +              "devise": {
      +                "type": "string"
      +              },
      +              "etat": {
      +                "description": "neuf = new, reconditionne = refurbished.",
      +                "enum": [
      +                  "neuf",
      +                  "reconditionne"
      +                ],
      +                "type": "string"
      +              },
      +              "lien_achat": {
      +                "description": "Affiliate link to the store page, through picksly.fr.",
      +                "type": "string"
      +              },
      +              "marchand": {
      +                "description": "Store selling the offer.",
      +                "type": "string"
      +              },
      +              "prix": {
      +                "type": "number"
      +              },
      +              "prix_releve_le": {
      +                "description": "Date (YYYY-MM-DD) the price was last read at the store.",
      +                "type": [
      +                  "string",
      +                  "null"
      +                ]
      +              }
      +            },
      +            "required": [
      +              "etat",
      +              "prix",
      +              "devise",
      +              "marchand",
      +              "prix_releve_le",
      +              "lien_achat"
      +            ],
      +            "type": "object"
      +          },
      +          "type": "array"
      +        },
      +        "remarque": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "marque",
      +        "modele",
      +        "annee",
      +        "notes",
      +        "criteres",
      +        "offres",
      +        "fiche"
      +      ],
      +      "type": "object"
      +    },
      +    "categorie": {
      +      "type": "string"
      +    },
      +    "comparaison": {
      +      "description": "Picksly page comparing the two models.",
      +      "type": "string"
      +    },
      +    "devise": {
      +      "type": "string"
      +    },
      +    "marche": {
      +      "type": "string"
      +    },
      +    "meilleur_par_profil": {
      +      "properties": {
      +        "budget": {
      +          "description": "Model with the higher score for this profile, \"egalite\" when equal, null when one score is missing.",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "premium": {
      +          "description": "Model with the higher score for this profile, \"egalite\" when equal, null when one score is missing.",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "smart": {
      +          "description": "Model with the higher score for this profile, \"egalite\" when equal, null when one score is missing.",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        }
      +      },
      +      "required": [
      +        "budget",
      +        "smart",
      +        "premium"
      +      ],
      +      "type": "object"
      +    },
      +    "mention": {
      +      "description": "Affiliate disclosure.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "categorie",
      +    "marche",
      +    "devise",
      +    "a",
      +    "b",
      +    "meilleur_par_profil",
      +    "comparaison",
      +    "mention"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is settled structurally. The description adds what the response conceptually contains (scores, prices, profile winners, page link), but says nothing about ambiguity handling, unknown model names, or pagination/depth limits — notable for a tool whose whole value is a comparison.

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?

A single sentence with zero filler, leading with the core deliverable (side-by-side scores and prices) and then the secondary outputs. Nothing is repeated from the schema or annotations.

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 needn't restate return fields, and the read-only annotations cover the safety burden. What remains thin is the identifier format for the two model parameters; otherwise an agent has enough to call this 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 coverage is 60%: pays, langue, and categorie are documented in the schema, so the description's mention of 'category' adds little. Crucially, modele_a and modele_b have no schema descriptions, and the description does not say whether they expect a model name, slug, or ID — the highest-impact gap is left unaddressed.

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 description names a concrete operation (side-by-side comparison of two models in the same category) and enumerates the payload: scores, prices, per-buyer-profile winner, and the Picksly comparison page. It implicitly distinguishes itself from the single-model sibling fiche_modele, but never explicitly contrasts with fiche_modele or meilleurs_choix.

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 phrase 'two models of the same category' implies the applicable scenario and a constraint (both models must belong to the same categorie), but there is no explicit 'use this when…' or 'for a single model use fiche_modele instead'. The agent must infer routing among the three siblings.

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