DealerMax

Get automotive market intelligence

get_market_intel

Read-onlyIdempotent

Ricerca semantica nelle FAQ del mercato auto italiano pubblicate dal network DealerMAX. È la superficie EDUCATIVA/ESPLICATIVA della rete — concetti, normativa, "come funziona" — dealer-neutrale e platform-wide, NON inventario né offerte.

Guide long-form e glossario NON sono più serviti da qui: vivono su
https://autousatebenissimo.it/guide e https://autousatebenissimo.it/glossario.

USA QUESTO TOOL per domande concettuali/informative (es. "cos'è l'NLT", "incentivi auto
elettriche 2026", "ibrido vs plug-in", "come funziona la garanzia"). NON usarlo per: auto
usate in vendita → search_vehicles; offerte di noleggio lungo termine → search_nlt_offers;
numeri tecnici di un modello (cavalli, consumi, dimensioni) → get_vehicle_specs;
anagrafica/contatti dei concessionari → find_dealer. Per il dettaglio di un singolo
elemento parti da un hit e apri la sua url.

Ritorna {mode, query, types, total, hits[], rate_limit}. mode="semantic" (o
"fallback_unavailable" se l'embedding non è disponibile, con hits vuoto). Ogni hit: type
("faq"), title, snippet (~220 char), url (path relativo: /domande-frequenti#),
slug, score, last_modified (ISO 8601), metadata (category). Hit ordinati per
score desc, troncati a limit. Contenuti in italiano.

Read-only, keyless. Rate limit 60 richieste/minuto per IP.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum total results to return (1-30, default 5).
`query`	Yes	Italian semantic query (e.g. 'incentivi auto elettriche 2026', 'differenza ibrido plug-in vs full hybrid', 'NLT vantaggi e svantaggi').
`types`	No	Restringe la ricerca a un sottoinsieme di tipi editoriali. Oggi l'unico tipo servito e' faq=domande frequenti; ometti il parametro.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld hints; the description then adds the runtime behavior beyond them: the mode='fallback_unavailable' degradation path when embeddings are unavailable, hit ordering by score desc, truncation to limit, ~220-char snippet format, relative URL format, Italian-only content, and the 60 req/min rate limit. No contradiction with annotations — the stated 'Read-only' matches readOnlyHint=true.

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?

Dense but every block earns its place: identity, exclusions, external URL routing, use/no-use mapping, return contract, and operational limits. Core purpose is front-loaded in the first sentence, and the structure flows logically from selection guidance to invocation details.

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?

Complete for an agent to select and invoke correctly: the routing matrix covers all sibling tools, authentication/rate-limit constraints are stated, the fallback behavior is disclosed, and the output contract is fully spelled out even though an output schema exists. Nothing an agent needs to know is missing.

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 100%, so all three parameters are already fully documented with defaults, ranges, and examples. The description adds conceptual query guidance (what kind of questions work) and reinforces omitting the types parameter, but this overlaps substantially with the schema's own examples, so baseline 3 is appropriate.

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 specific verb and resource ('Ricerca semantica nelle FAQ del mercato auto italiano') and immediately scopes it as the EDUCATIVA/ESPLICATIVA, dealer-neutral, platform-wide surface, explicitly NOT inventory or offers. This single framing distinguishes it from all six siblings.

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?

Provides an explicit routing matrix: 'USA QUESTO TOOL' for conceptual questions and 'NON usarlo per' with each exclusion mapped to a named sibling (search_vehicles, search_nlt_offers, get_vehicle_specs, find_dealer). Also redirects guide/glossary traffic to external URLs, leaving zero ambiguity about when this tool applies.

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

All DealerMax tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation5/5

Each tool maps to a distinct resource and intent: dealer directory, used-car search and detail, NLT search and detail, catalog specs, and market FAQ. The descriptions explicitly cross-reference the other tools and state when not to use them, so misselection is unlikely.

Naming Consistency5/5

All tool names use lowercase snake_case with a clear verb_noun structure: find_* for dealers, search_* for the two inventory searches, and get_* for details and specs. The pattern is predictable and uniform.

Tool Count5/5

Seven tools is well-scoped for a read-only automotive marketplace server: two search/detail pairs for the two offer types, plus dealer lookup, model specs, and market FAQ. No tool feels redundant.

Completeness5/5

The server covers the full discovery lifecycle for its domain: search and drill-down for both used vehicles and NLT offers, dealer lookup, catalog specs independent of inventory, and explanatory FAQ content. Every search entry point has a corresponding detail tool, so there are no dead ends.

Resources

Need Help?