Real-time fuel prices, active alerts (traffic, wildfires, severe weather, earthquakes), per-country data coverage, and cheapest gas stations by city, aggregated from official public sources across 38+ countries. Read-only, no auth required for the free tier.
Scored across 4 tools
The four tools target fairly distinct resources: alerts, per-city station prices, country coverage, and national fuel averages. The only mild overlap is between ekopump_get_fuel_prices (national averages) and ekopump_get_city_stations (per-station city prices), but descriptions clearly delineate scope.
All tools follow a strict, predictable ekopump_get_<noun> snake_case pattern. No mixing of conventions or verb styles.
Only 4 tools for a platform whose coverage tool advertises many live data domains (transit, live vehicles, bikes, EV chargers, flights, ships). The count is thin relative to the apparent breadth, though each of the four earns its place.
Core retrieval exists for alerts, fuel prices, and city stations, but the coverage tool reveals many advertised data types (public transit, live vehicles, public bikes, EV chargers, flights, ships) with no corresponding tools to fetch them. This is a notable gap agents cannot work around.
Devuelve las alertas actualmente activas que EkoPump agrega de múltiples fuentes oficiales: tráfico DGT (España), incendios (EONET/EFFIS), meteorología severa (MeteoAlarm, National Weather Service), sismos y otras. Incluye desglose por fuente y severidad además de una muestra de alertas individuales.
Args:
limit (number, opcional, 1-50, por defecto 15): cuántas alertas individuales devolver. El desglose por fuente/severidad siempre refleja el total real, no solo la muestra.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Número máximo de alertas individuales a devolver (1-50, por defecto 15). El resumen por fuente y severidad siempre incluye el total real. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds useful behavioral context about aggregating from multiple official sources and clearly explains that the source/severity breakdown reflects the total real count, not just the sampled alerts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: two sentences plus a clearly formatted Args section. Information is front-loaded with the main purpose, and no words are wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter, read-only tool with no output schema, the description adequately covers what the tool returns (breakdown by source/severity and a sample of individual alerts), the sources involved, and the limit behavior. Annotations handle safety context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully describes the limit parameter with range, default, and the note about the breakdown always reflecting the total. The description repeats this information without adding new semantic details, so it aligns with the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns currently active alerts aggregated from multiple official sources, listing specific source types (DGT, EONET/EFFIS, MeteoAlarm, NWS). This distinguishes it from sibling tools that focus on stations, coverage, and fuel prices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The usage context is implied by the description—this tool is for retrieving active alerts—but there is no explicit guidance on when to use it versus the sibling tools or when not to use it. No alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve las gasolineras con mejor precio en una ciudad concreta cubierta por EkoPump, ordenadas de más barata a más cara, con precio de gasolina y diésel por estación.
Args:
city (string, requerido): nombre o slug de la ciudad (ej. "Madrid", "paris"). Debe ser una de las ciudades cubiertas por EkoPump — si no se reconoce, el error incluye ejemplos válidos.
limit (number, opcional, 1-25, por defecto 10): cuántas estaciones devolver.
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes | Nombre o slug de una ciudad cubierta por EkoPump (ej. "Madrid", "paris", "san-sebastian"). Ciudades disponibles: Madrid, Barcelona, Valencia, Sevilla, Bilbao, Zaragoza, Málaga, Alicante, Murcia, Palma, Valladolid, Córdoba, Granada, Santander, San Sebastián, y más. | |
| limit | No | Número máximo de estaciones a devolver, ordenadas de más barata a más cara (1-25, por defecto 10). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds useful behavioral context: the error behavior when a city is not recognized, the default and range for limit, and the ordering of results. This goes beyond annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a clear purpose sentence followed by parameter explanations in a standard args format. Every sentence adds value, and the front-loaded purpose ensures quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter read-only tool with no output schema, the description adequately explains what is returned (stations, prices for gasoline and diesel, ordering). It does not specify exact field names, but given the tool's simplicity and good annotations, this is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents both parameters well. The description repeats this information but adds the detail that invalid city errors include valid examples, which is not in the schema. This is a small increment, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns gas stations with the best prices in a specific city, ordered from cheapest to most expensive, including gasoline and diesel prices. This is a specific verb+resource combination that distinguishes it from siblings like 'get_country_coverage' and 'get_active_alerts'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies when to use it (for city-specific fuel price queries) and mentions the city must be covered by EkoPump. However, it does not explicitly state when not to use it or mention alternative tools for broader coverage, though sibling names make this reasonably clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve qué tipos de datos en vivo tiene EkoPump para un país (o para todos): combustible, transporte público, vehículos en vivo, bicis públicas, cargadores EV, alertas locales, vuelos y barcos. Útil para responder "¿EkoPump tiene datos de X país?" o "¿qué cubre EkoPump en Portugal?".
Args:
country (string, opcional): código ISO 3166-1 alpha-2 (ej. "PT"). Si se omite, devuelve un resumen agregado de todos los países con al menos un dato en vivo.
| Name | Required | Description | Default |
|---|---|---|---|
| country | No | Código de país ISO 3166-1 alpha-2. Si se omite, se devuelve un resumen agregado de todos los países. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive, and the description adds context by explaining the aggregated summary behavior when country is omitted. It also enumerates the data types covered, clarifying what 'coverage' means without contradicting annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: two sentences plus an Args block, with the core function stated upfront. The Args block is somewhat redundant with the schema, but the overall length is appropriate and contains no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description carries the burden of explaining return behavior. It states it returns the types of live data available per country, which is sufficient for a simple lookup tool, though the exact return format (e.g., list of strings) is not specified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully describes the country parameter (ISO code, optional, omitted behavior) with 100% coverage, providing a baseline of 3. The description's Args section repeats this but adds an example ('PT'), offering a minor enhancement beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns live data coverage types per country (or all countries), listing eight data categories (e.g., combustible, transporte público). It distinguishes from sibling tools that focus on specific data types by being a coverage overview for a country. The verb 'Devuelve' plus resource makes the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases, such as answering whether EkoPump has data for a country or what it covers in Portugal. It explains the optional country parameter's behavior (aggregate summary when omitted). However, it does not directly state when not to use this tool versus sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve el precio medio nacional de gasolina (G95), G98 y diésel por país, junto con el precio del petróleo Brent, agregados a partir de fuentes oficiales por EkoPump (ekopump.es). Datos de solo lectura, sin autenticación.
Args:
country (string, opcional): código ISO 3166-1 alpha-2 (ej. "ES"). Si se omite, devuelve todos los países disponibles.
Precios por litro. Cada país trae su campo "currency" (ISO 4217): EUR en la mayoría; algunos países se devuelven en su moneda local sin convertir (p. ej. TRY, BRL, VND). No compares países con monedas distintas sin convertir antes.
| Name | Required | Description | Default |
|---|---|---|---|
| country | No | Código de país ISO 3166-1 alpha-2 (ej. 'ES', 'FR', 'DE'). Si se omite, se devuelven todos los países con datos de precio disponibles. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the read-only, idempotent, closed-world profile, so the description correctly focuses elsewhere. It adds genuine behavioral context the annotations cannot convey: each country carries a 'currency' field, some countries are returned in local currency unconverted (TRY, BRL, VND), and cross-currency comparisons must be converted first. Only return-shape/pagination detail is absent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loads the purpose, then arg semantics, then currency caveats as a separate closing paragraph, so nothing important is buried. The sentence 'Datos de solo lectura, sin autenticación' is mild redundancy against the readOnlyHint annotation and openWorldHint=false, but the rest earns its space.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description carries the return-value burden and does so by specifying units (price per litre) and the per-country 'currency' field with the unconverted-currency warning. Combined with the annotated safety profile, an agent has everything needed to call and interpret this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the ISO 3166-1 alpha-2 code and the omit-to-return-all behavior. The description repeats this and adds an example ('ES'), which is a marginal gain over the structured field, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Devuelve el precio medio nacional de gasolina G95, G98 y diésel por país' plus Brent) and names the aggregation source. The scope is clearly distinct from the sibling tools (alerts, city stations, country coverage), so an agent can route correctly 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains the trigger condition for the single parameter ('Si se omite, devuelve todos los países disponibles') and notes it is read-only with no authentication. It gives clear usage context but does not explicitly reference alternatives among the sibling tools for related price/coverage questions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
ekopump_get_active_alertsekopump_get_city_stationsekopump_get_country_coverageekopump_get_fuel_prices
Add one secure layer between your agents and this server.