Skip to main content
Glama
Sign In

normi

by io.github.NormiHQ
OverviewDiscussionsAdmin

Analyze Market Statistics

analyze_market_statistics
Read-only

Get market statistics: avg/median prices, price per m², surface areas.

REQUIRED: You MUST provide at least one location filter:

  • code_postal (e.g., "75011")

  • commune (e.g., "PARIS 11" - uppercase; Paris uses "PARIS 01"–"PARIS 20")

  • code_departement (e.g., "75")

  • latitude + longitude for radius search

Examples:

  • Paris 11e market: {commune: "PARIS 11", type_local: "Appartement"}

  • 500m radius: {latitude: 48.8566, longitude: 2.3522, radius_m: 500}

  • Department stats: {code_departement: "69", type_local: "Maison"}

Returns: count, price (min/max/avg/median), surface stats, price_per_m2. The figures leave out the scope's lowest and highest 1% price per m² (outliers_excluded, 20+ sales); count is every matching sale.

Note: radius_m > 1000m is automatically restricted to the last 12 months of data.

Cost: 5 credits per call

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "analyze_market_statistics"
  }
}

Input Schema

NameRequiredDescriptionDefault
communeNoCity/commune name (e.g., 'Paris', 'Lyon')
date_finNoEnd date (YYYY-MM-DD)
latitudeNoLatitude for radius search (requires longitude)
radius_mNoRadius in meters for location search (default: 500)
longitudeNoLongitude for radius search (requires latitude)
date_debutNoStart date (YYYY-MM-DD)
type_localNoProperty type
code_postalNoPostal code (e.g., '75001')
exclude_vefaNoExclude VEFA (new-build, vente en l'état futur d'achèvement) sales (default: true — keeps 'ancien' results from double-counting new-build activity)
include_terrainNoInclude terrain-only transactions in search results (default: false)
code_departementNoDepartment code (e.g., '73' for Savoie, '83' for Var)
use_original_typeNoUse original type_local instead of smart computed_type_local (default: false)
exclude_bulk_salesNoExclude bulk sales and aggregated transactions (default: true for clean market data)
include_pouvoir_achatNoAdd a price-to-income ratio field (INSEE Filosofi × DVF). Ignored on radius searches.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / exclude_outliers
      Removed value: -{
-  "default": true,
-  "description": "Exclude price outliers (default: true for clean market data)",
-  "type": "boolean"
-}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnly/closed-world annotations, the description discloses non-obvious behavior an agent could not infer: percentile trimming of the highest and lowest 1% price per m² (only with 20+ sales), the fact that count still reflects every matching sale, and that radius_m > 1000m is silently restricted to the last 12 months. It also exposes cost (5 credits) and a parameter interaction (include_pouvoir_achat ignored on radius searches).

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 output summary and the mandatory-filter constraint are front-loaded, followed by short bullet lists and worked examples rather than prose. Every line carries operational information (formats, defaults, limits, cost) with no filler.

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?

For a 14-parameter, no-output-schema tool, the description supplies the missing return shape (count, price min/max/avg/median, surface stats, price_per_m2) and caveats about how those figures are computed. Nothing an agent needs to construct a valid, correctly-interpreted call appears to be absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description adds real meaning the schema lacks: the commune format requirement (uppercase, 'PARIS 01'–'PARIS 20') which actually corrects the schema's lower-case 'Paris' example, the latitude+longitude pairing rule, and the radius_m > 1000m degradation. It does not explain exclude_bulk_sales, exclude_vefa, or use_original_type beyond what the schema already states.

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 clause names a specific verb and resource plus the exact metrics returned (avg/median prices, price per m², surface areas), so an agent knows this is the aggregate-statistics tool rather than a raw-transaction search. It never names a sibling (e.g. analyze_price_trends, search_property_transactions, get_zonal_price_distribution) to draw an explicit boundary, so it lands at 4 rather than 5.

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?

It states a hard precondition — at least one of code_postal, commune, lat+long — and enumerates the acceptable filter shapes with three concrete call examples, which is strong when-to-use guidance. It stops short of exclusions, never saying when to prefer a sibling tool or which data cannot be answered this way.

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

All normi toolsInspect
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