Skip to main content
Glama

DatiTuristici.it

Read the projection of an Italian comune with uncertainty and reliability

leggi_previsioni_comune
Read-onlyIdempotent

Reads the statistical projection of one Italian municipality (comune) for the year after the latest ISTAT year: total, hotel and non-hotel nights and arrivals. Use it when you have the 6-digit cod_istat from cerca_comune and the question is what to expect next; do not use it for past figures (use leggi_serie_comune instead) or to set comuni side by side (use confronta_comuni instead). Each line gives last year's real figure, the projected figure and affidabilita_pct (0 to 100, measured by projecting a past year), and only the total has the p10 to p90 uncertainty band; a line that fails the checks has disponibile false and a motivo, a comune without a yearly series returns an empty list in linee with a nota, and a missing figure is null. These are estimates, not official statistics, and they are served only while the site shows projections to everyone, otherwise the call returns an error. Read-only, public, no authentication; 30 requests per minute per client, shared across tools.

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": {
      "cod_istat": "<cod_istat>"
    },
    "name": "leggi_previsioni_comune"
  }
}

Input Schema

NameRequiredDescriptionDefault
cod_istatYes6-digit ISTAT code of the comune as a string, leading zeros kept ("058091" is Roma); it comes from cerca_comune. An unknown code returns an error that says what to pass.

Output Schema

NameRequiredDescriptionDefault
nomeYesOfficial name of the comune.
notaYesNotes in English on reading the projection: what it is, how the total and its band are built when the year adds any months ISTAT has already published, which lines are not projected and why, which may be derived from the total, where reliability is missing, and the change of ISTAT scope in 2025. When no projection is stored, it says so.
fonteYesSource to cite with the figures: processed by DatiTuristici.it from institutional data (ISTAT).
lineeYesThe four lines in the order totale, alberghieri, extra, arrivi; an empty list when no projection is stored for this comune (see `nota`).
metodoYesName of the statistical model that made the projections; null when none is stored.
schedaYesLink to the comune's public page on datituristici.it, to cite.
cod_istatYes6-digit ISTAT code of the comune, as a string with leading zeros kept.
anno_orizzonteYesThe one year projected: the year after the latest year with ISTAT yearly figures. Null when no projection is stored for this comune (see `nota`).
soglia_affidabilita_bassaYesReliability percentage below which the site labels a projection as low; null when no projection is stored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, but the description adds substantial context beyond them: estimates are not official statistics, calls fail if the site stops showing projections publicly, and there is a 30 req/min per-client limit shared across tools. It also discloses output behaviors (affidabilita_pct, p10–p90 band only on the total, disponibile/motivo on failed checks, nota plus empty linee when no series, null for missing figures).

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?

It is front-loaded with purpose, then routing, then output semantics, and essentially every clause carries information. It is a single dense run-on paragraph, though, which makes the return-value details harder to scan than a structured list would be.

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?

Even though an output schema exists, the description explains the non-obvious return semantics (reliability percentage, uncertainty band limited to the total, unavailable lines with motivo, empty linee with nota) plus availability gating and rate limits. An agent has everything needed to call it and interpret the response.

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?

Schema coverage is 100% and the schema already documents the 6-digit pattern, leading-zero preservation and the unknown-code error, so the schema carries most of the weight. The description adds marginal value by tying the value's provenance to cerca_comune and reinforcing the format requirement, but does not go beyond what the schema states about error behavior.

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 ('Reads the statistical projection of one Italian municipality') and immediately scopes the output (total, hotel and non-hotel nights and arrivals for the year after the latest ISTAT year). It names the sibling tools it is not (leggi_serie_comune, confronta_comuni), so an agent can select it without opening any schema.

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?

It states the positive condition ('when you have the 6-digit cod_istat from cerca_comune and the question is what to expect next') and two explicit exclusions with the alternative for each: past figures → leggi_serie_comune, side-by-side comparison → confronta_comuni. Nothing about when to invoke is left to inference.

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