mcp-server

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

Las anotaciones ya cubren readOnlyHint, idempotentHint y openWorldHint, por lo que la barra de transparencia obligatoria es baja. La descripción añade valor al revelar el contenido de la «ficha» (servicios, accesibilidad, URL canónica), el alcance geográfico y el carácter vigente de la bandera. No contradice ninguna anotación.

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?

Dos frases compactas que sitúan el propósito principal al principio y presentan inmediatamente los filtros disponibles. No hay repetición de la información del schema ni relleno innecesario.

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?

Para una herramienta de consulta de solo lectura, idempotente y de mundo abierto, la descripción cubre alcance, criterios de filtrado y contenido de retorno a pesar de no haber output schema. Podría ser más explícita sobre la forma de la lista o los valores posibles de la bandera, pero el agente tiene suficiente información para invocarla correctamente con parámetros opcionales.

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?

Los tres parámetros tienen descripciones en el schema, por lo que la cobertura es del 100% y se aplica el nivel base. La descripción añade la relación entre beach y municipality con «Acota por nombre de playa o municipio», pero no aporta nada nuevo sobre limit. El valor añadido es útil pero limitado.

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?

La descripción identifica claramente el recurso (playas de Alicante y municipios próximos) y el contenido devuelto: bandera vigente, estado, servicios, accesibilidad y URL canónica. Aunque no emplea un verbo principal como «devuelve» u «obtiene», la instrucción «Acota por nombre de playa o municipio» precisa la operación. El ámbito específico de playas la distingue de herramientas hermanas genéricas como find_place o weather_now.

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?

La frase «Bandera vigente y estado de las playas» implica cuándo usar la herramienta: cuando se necesita información actual de bandera, servicios o accesibilidad de playas en Alicante. Sin embargo, no menciona explícitamente alternativas ni cuándo no usarla, dejando la decisión de routing a la inferencia del agente.

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

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

Annotations already provide readOnlyHint and openWorldHint. The description adds meaningful behavioral context by explaining the ETA source priority (official real-time data, falling back to the own estimation engine) and describing the computed outputs. There is no contradiction with the annotations; the real-time nature even helps justify why idempotentHint is false.

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 two dense sentences with no filler. The first sentence defines the task and the calculation logic; the second states the outputs. Key information is front-loaded and every part earns its place.

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?

With no output schema, the description takes on the burden of explaining return values, and it does so by naming the four decision outcomes, the margin, and the next reachable step. However, it leaves 'siguiente paso alcanzable' somewhat ambiguous and does not describe failure behavior for missing ETA or invalid stops, though UNKNOWN partially covers that.

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 baseline applies: the schema already documents each parameter with ranges, defaults, and purpose. The description provides a useful global context by linking lat/lng and walk_speed_ms to the walking-time calculation, but it does not add much detail beyond what the schema already conveys.

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 names a specific action ('Decide si el usuario llega a tiempo a un autobús'), a concrete resource (a bus stop in Alicante), and the core method (comparing vehicle ETA with walking time). It also lists the decision outputs (CATCH, TIGHT, MISS, UNKNOWN), which clearly distinguishes it from siblings such as next_departures or find_transit_stop.

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 triggering scenario is explicit: use this tool when the user needs to know whether they can reach a bus on time at an Alicante stop. However, it does not discuss alternatives or when not to use it, such as when the user only wants departure times (next_departures), so it stops short of full exclusion guidance.

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

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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, so safety and idempotency are declared. The description adds useful context about the content of the contract (freshness, official sources, access policy) and the necessity of calling it first, which goes beyond the 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?

Two concise sentences. The first states the core purpose and enumerates the contract contents; the second gives a clear usage directive. No fluff, and the critical info is front-loaded.

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?

Given the absence of an output schema, the description enumerates the categories of information returned (sections, data types, freshness, sources, access policy) and frames it as a 'data contract', which sufficiently tells an agent what to expect. For a discovery tool used as an entry point, this is complete.

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 tool has zero parameters, so the input schema is empty and the description need not elaborate. Per guidelines, baseline for 0 parameters is 4; description does not mislead or add unnecessary detail.

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 the data contract of VamosAlicante, listing specific elements (sections, data types, freshness, sources, access policy). It uses a specific verb ('Devuelve') and distinguishes itself from siblings by instructing to call it first when unsure which tool to use.

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?

Explicitly says 'Llamar primero cuando no se sabe qué herramienta usar' — a direct when-to-use instruction. It implies when to use alternatives (when you know the tool), and the discovery purpose is unambiguous.

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

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

The description adds substantial behavioral detail beyond the readOnly/openWorld/idempotent annotations: it discloses the official live data source (Alicante se mueve API), the on-demand fetching policy, the fallback to a predictive estimated_eta (clearly marked ESTIMATED), and the explicit rule never to use stale cached arrivals. This is exactly the transparency an agent needs to reason about data freshness and reliability.

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 one dense paragraph that front-loads the core purpose and then covers critical data-freshness and fallback behavior. It is written in Spanish, consistent with the title, and every sentence contributes useful information. It is slightly long but not wasteful.

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 read-only tool with a single parameter and no output schema, the description is quite complete: it specifies the returned fields (name, coordinates, lines, arrivals) and the crucial live-data/fallback policy. It does not detail the exact output structure, but that is acceptable given the tool's simplicity and the schema's clarity.

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 input schema fully documents the single 'stop' parameter with a format pattern and an example. The description adds no additional meaning about the parameter beyond what the schema already provides, so the baseline score of 3 applies given the 100% schema description 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 retrieves a complete record of a specific bus stop (name, coordinates, lines) along with upcoming arrivals. It specifies the resource and the action, but it does not explicitly differentiate from sibling tools like find_transit_stop or next_departures, so it stops short of a 5.

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?

There is no explicit guidance on when to use this tool over alternatives. The description implies it is for a specific known stop but never says 'use when you already have the stop code' or contrasts with find_transit_stop or next_departures. No exclusions or alternative recommendations are provided.

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

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

Annotations already cover read-only, open-world, and idempotent behavior; the description adds valuable constraints by specifying returned fields (address, published hours, dish/price when available) and explicitly stating 'No devuelve cartas completas'. This goes meaningfully beyond the structured hints and contradicts nothing.

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?

Three concise sentences that front-load the purpose, follow with the return contract, and close with an explicit non-return. 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?

With no output schema, the description still communicates the essential return fields and the main boundary. It does not explain parameter combinations or empty-result behavior, but the openWorldHint and parameter descriptions cover much of the remaining 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?

Schema description coverage is 100%, so the structured parameters carry most of the semantic weight. The description reinforces dish, cuisine, and name with examples but adds little beyond the schema, and limit is not mentioned in prose.

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 states a concrete purpose: resolving a gastronomic need in Alicante by dish, cuisine, or place name. It is clear about the resource and scope, but it does not explicitly distinguish it from sibling tools like find_place or search_alicante.

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?

Usage is implied by the concrete query examples ('un plato, una cocina o un local por nombre') and the exclusion of full menus. However, it never states when not to use this tool or names an alternative, so the agent must infer the boundary against siblings.

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

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

Annotations already cover read-only, open-world, and idempotent behavior, so the safety profile is handled. The description adds the 'requires narrowing' constraint and the pharmacy guard detail, but does not disclose result behavior, empty-result handling, or matching semantics. This is acceptable given the annotations, but not rich.

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 one compact sentence that front-loads the core purpose and then lists the supported categories. The closing constraint is valuable and there is no filler, though the category enumeration is fairly long.

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 search tool with seven parameters and no output schema, the description could usefully explain result presentation, empty-result behavior, or how to structure narrowed queries. It covers the domain and the narrowing requirement, and annotations cover safety, so it is minimally sufficient but not complete.

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 all seven parameters. The description loosely maps to parameters like name→query, zona→zone, and categoría→category, and mentions guard pharmacies (onDuty), but it adds no new format or constraint details 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 uses a clear verb and resource: 'Busca un sitio o servicio concreto de Alicante' and enumerates specific categories. It defines the tool's scope well, though it does not explicitly distinguish it from sibling tools like search_alicante or find_food, so it stops short of a 5.

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 instruction 'Exige acotar la consulta' gives a useful constraint and the category list implies when to use the tool. However, it provides no explicit when-to-use versus alternatives or exclusion conditions, leaving some selection to the agent's inference.

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

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

Annotations already establish read-only, open-world, and idempotent behavior. The description adds useful behavioral traits: it does not return the full stop list and it requires a search term. This goes beyond annotations, though the 'requiere nombre o línea' claim is not reflected in the schema's required fields.

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?

Two sentences carry all essential information: search scope, output, downstream workflow, and a key limitation. There is no fluff or repetition of the schema.

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 tool without an output schema, the description helpfully states the return fields and workflow. However, the mismatch between the stated requirement ('nombre o línea') and the input schema (only network required) leaves an agent unsure how to construct a valid call. It also does not clarify how query and line interact when both are provided.

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 baseline is 3. The description adds some meaning by clarifying that query or line is the search key and that results include code, lines, and coordinates. However, it creates ambiguity by saying 'requiere nombre o línea' while the schema only marks network as required.

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 uses a specific verb ('Busca') and names a clear resource ('parada de autobús urbano o una estación de TRAM de Alicante'), plus the expected outputs ('código, líneas y coordenadas'). It also differentiates the tool from next_departures by explaining this is a prerequisite lookup step.

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?

It gives clear usage context: the agent should use this tool to find a stop by name or line, then call next_departures for upcoming departures. It also states a precondition, 'Requiere nombre o línea', but does not explicitly compare against sibling search tools like find_place or search_alicante.

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

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

Annotations already carry readOnlyHint, openWorldHint, and idempotentHint, so the description does not need to cover safety. It adds some behavioral context by mentioning status and published time and the scoping behavior, but it does not disclose things like data freshness, response size, or timezone behavior beyond what the schema notes.

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?

Two compact sentences with no filler. The first sentence states the resource and output, and the second clarifies the intended scoping behavior. Every word earns its place.

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 read-only query tool with a fully documented schema, the description provides the essential user-facing semantics: scope by city/date and include status and published time. It does not describe the exact response structure, but no output schema is present and the description covers the core invocation context sufficiently.

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 fully documents all four parameters. The description mentions 'city or date' but does not add meaning beyond the schema, so the baseline score of 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 identifies the resource (Alicante-Elche airport arrivals/departures) and the key output (status and published time), and it states the scoping behavior by city or date. However, it does not explicitly differentiate itself from sibling tools like next_departures or search_alicante, so it stops short of a 5.

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 gives useful context on when to use the tool: narrow by city or date instead of requesting the full daily list. It does not name alternative tools or exclusion cases, but the guidance is clear enough for an agent to select this tool for flight-specific queries.

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

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

Las anotaciones ya cubren readOnlyHint, openWorldHint e idempotentHint, por lo que la barra es más baja. La descripción añade contexto útil más allá de las anotaciones: los precios son oficiales, el orden es ascendente por precio y se incluyen rótulo, dirección y fecha de publicación. Esto comunica el comportamiento de salida sin contradecir las anotaciones.

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?

Es una sola frase sin relleno que va directa al grano: fuente oficial, ámbito geográfico, criterio de ordenación y campos devueltos. Todo el contenido aporta valor y está bien estructurado.

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?

Para una herramienta sencilla, la descripción cubre el recurso, orden y campos de salida, pero deja ambigüedad: dice que es 'para un carburante concreto' mientras que ningún parámetro es obligatorio, sin explicar qué ocurre si se omite fuel. Tampoco detalla el comportamiento de query ni el límite por defecto, aunque el esquema sí define el máximo.

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?

El esquema documenta el 100% de los parámetros, por lo que el punto de partida es 3. La descripción refuerza la idea de que el parámetro fuel es el eje central ('para un carburante concreto'), pero no añade detalles sobre limit ni query que no estén ya en el esquema. Cumple sin superar la línea base.

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?

La descripción define con precisión qué devuelve la herramienta: precios oficiales de carburante en gasolineras de Alicante, para un carburante concreto, ordenados de más barato a más caro, e incluye los campos principales (rótulo, dirección y fecha oficial). Aunque no usa un verbo explícito como 'consultar' u 'obtener', el recurso y el alcance quedan claros y se distinguen fácilmente de herramientas hermanas como find_food o find_place.

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?

El uso se infiere de la descripción: sirve para obtener precios oficiales ordenados de un carburante específico en Alicante. Sin embargo, no menciona explícitamente cuándo usarla frente a alternativas como search_alicante, ni indica exclusiones o casos en los que otra herramienta sería más adecuada.

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

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

Beyond the readOnlyHint/openWorldHint annotations, the description reveals the on-demand official data source for bus stops, the fallback to estimated_eta labeled ESTIMATED when LIVE fails, and the explicit prohibition against using old cached arrivals as current state. This is valuable behavioral disclosure.

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?

Three dense sentences with no wasted words; the purpose is front-loaded and each sentence earns its place, including the essential fallback and data-freshness rule.

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 invocation, the description is complete: it gives the required parameter, source, and fallback behavior. However, with no output schema, it doesn't describe the returned structure for non-bus entity types (parking, beach, TRAM), which is a minor gap given the tool's multi-type scope.

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 baseline is 3, but the description adds meaning: it states that entity_id is exactly what resolve_entity returns and explains the bus-stop:<código> prefix behavior, going beyond the schema's basic identifier format.

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 states a specific verb and resource ('Estado ahora mismo de una entidad concreta ya identificada') and enumerates concrete entity types (parking, bus stop, TRAM, beach). It distinguishes itself from resolve_entity by explicitly requiring the entity_id that resolve_entity returns.

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?

It gives clear context: the tool must be used on an already-identified entity, and it specifies special handling for bus-stop codes. It does not, however, name sibling alternatives like next_departures or parking_availability or state explicit when-not conditions, so it stops short of a 5.

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

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

Las anotaciones ya declaran readOnlyHint=true, openWorldHint=false e idempotentHint=true, cubriendo el perfil de seguridad. La descripción añade que devuelve el contenido 'actual', lo que sugiere frescura de datos, pero no informa sobre posibles límites de tamaño, formato exacto o manejo de errores. Con anotaciones presentes, la descripción aporta un valor adicional modesto.

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?

La descripción es una sola oración, directa y sin relleno. Incluye la acción, el recurso, el destino (agentes de IA) y el formato de retorno, todo en una estructura compacta y fácil de procesar.

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?

Para una herramienta sin parámetros, sin esquema de salida y con anotaciones que declaran idempotencia y solo lectura, la descripción es suficiente para comprender su propósito y uso. Carece de detalles sobre el tamaño esperado o posibles errores, pero estos son poco críticos para una consulta simple de un archivo estático.

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?

La herramienta no tiene parámetros, y la descripción especifica claramente qué recurso se consulta y qué se devuelve, lo que elimina ambigüedad. Sin parámetros por documentar, la descripción cumple con la función de contexto del recurso. La cobertura del esquema es 100% (vació), así que no se requiere compensación adicional.

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?

La descripción combina un verbo específico ('Devuelve'), un recurso concreto ('/llms-full.txt de VamosAlicante') y el formato de salida ('texto plano para agentes de IA'). Esto distingue claramente la herramienta de sus hermanas, que abordan dominios diferentes como playas, transporte o comida.

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?

La descripción indica el contexto de uso ('para agentes de IA') y que devuelve el contenido actual del archivo. Aunque no menciona explícitamente alternativas ni cuándo no usarla, la ausencia de parámetros y el nombre descriptivo hacen evidente que es una herramienta de consulta simple; el contexto es suficientemente claro.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and idempotentHint=true, so the safety profile is covered. The description adds the return format ('texto plano') as a behavioral detail, but nothing else — no mention of content size, freshness, or how links within the document should be handled.

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?

Two sentences, each earning its place: the first states the action and output format; the second provides context about the resource's purpose for AI agents. No redundancy and 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?

For a zero-parameter, no-output-schema, read-only tool, the description is nearly complete. It states what is returned, in what format, and why the resource matters (instructions/resources for AI agents). A brief note that the content may be lengthy or contain links to other endpoints would push it to a 5, but nothing essential is missing.

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 tool takes zero parameters and schema coverage is 100% (an empty properties object). Per rubric, 0 params earns a baseline of 4. Parameter semantics are a non-issue here since there is nothing to configure.

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 states a specific verb ('Devuelve') and a specific resource ('/llms.txt de VamosAlicante'), and clarifies the output format ('texto plano'). It is clearly distinguishable from all sibling tools, none of which relate to llms.txt — siblings cover beaches, vehicles, food, places, transit, parking, weather, and events.

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 second sentence notes the resource contains 'instrucciones y recursos destinados a agentes de IA', which implies the tool is useful when an agent needs site-specific guidance. However, there is no explicit statement of when to use it over alternatives or when not to use it.

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

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

Even though annotations already mark the call as read-only/idempotent, the description adds real operational transparency: it names the official live endpoint, says the bus query always hits it on demand, and reveals the exact fallback (`estimated_eta`) with an explicit ESTIMATED label. This is exactly the kind of behavioral context annotations cannot convey.

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 purpose, preconditions, and bus-specific behavior are front-loaded in four dense sentences with no filler. The endpoint path is specific but earns its place by clarifying the authoritative source.

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?

With no output schema, the description doesn't describe the response shape or fields beyond mentioning `estimated_eta` in fallback. It also omits error/rate-limit behavior and how to resolve stop identifiers, so while it's adequate for invocation, it has clear completeness gaps.

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?

Input schema descriptions cover 100% of parameters, so the baseline is already solid. The description adds extra semantic meaning by mapping 'servicio' to mode and 'parada o destino' to stop/destination, and by explaining the live-vs-fallback behavior that affects how mode=bus results should be interpreted.

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 opening sentence names the resource ('servicio concreto de Alicante') and enumerates the five transport modes (bus, TRAM, Cercanías/ADIF, coach, C6), so an agent can tell this is a transit-query tool. It lacks an explicit main verb such as 'return' or 'get' and does not name sibling tools for differentiation, so it stops just short of top score.

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 states the precondition clearly: 'Requiere identificar el servicio y la parada o el destino' and explains mode=bus behavior. It does not mention when to prefer a sibling like find_transit_stop to obtain missing stop/destination codes or when to avoid the tool.

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

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

The annotations already indicate a read-only, idempotent, open-world operation. The description adds meaningful behavioral context by explaining that the result shape depends on whether a live sensor observation is current or only a catalog entry exists, and it explicitly mentions the `dataType` field distinguishing LIVE from CATALOG.

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 compact and front-loaded: the first clause states the core purpose, followed by a concise explanation of the conditional response and the key dataType field. No sentences are wasted, and the structure is easy to parse.

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 no-parameter tool with no output schema, the description gives enough information to understand the general response shape, including plausible fields such as capacity, address, and tariff. It could be more explicit about what happens when no sensor observation and no catalog entry exist, but the core calling context is adequately covered.

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 tool has zero parameters, so the baseline is 4. The description does not need to explain input semantics and adds relevant context about the output's dataType indicator, which is useful even though it is not an input parameter.

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 that the tool returns the status of public parking in Alicante, including free spaces under live sensor observation and catalog details when only catalog data exists. It is specific about the resource and scope, though it uses a noun phrase rather than a strong imperative verb and does not explicitly differentiate itself from sibling tools.

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 intended use case is implied through the domain-specific content about Alicante parking availability, so an agent can infer when to use it. However, there is no explicit guidance about when not to use this tool or what alternative to choose, leaving usage selection to inference.

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

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

Annotations already indicate readOnly, idempotent, and openWorld behavior. The description adds genuinely useful behavioral detail: fuzzy matching tolerates accents, aliases, and typos; the output is a stable identifier; and an `ambiguous` response should trigger a clarifying user question. It does not mention not-found/error behavior, but the provided traits go well beyond the 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?

Three sentences, with the core conversion front-loaded and no redundant phrasing. The usage hint and ambiguity-handling instruction each earn their place.

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?

With no output schema, the description does well to mention the stable `entityId` and the `ambiguous` signal. It covers input flexibility, type restriction, and the follow-up behavior. It omits explicit not-found behavior and a full response shape, but for a two-parameter resolver this is a minor gap.

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 baseline is 3. The description adds extra meaning by framing `query` as loose user speech and by explaining that `type` narrows among parking, tram-stop, bus-stop, and beach. It also ties the query to the stable `entityId` output, which is not explicit in 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 a specific action: converting a user-spoken name with typos, aliases, or accents into a stable `entityId` for one of four Alicante entity types. It also positions itself as the prerequisite step for `get_current_state`, which helps distinguish it from search-oriented siblings like `search_alicante` or `find_transit_stop`.

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 gives explicit usage context: 'Primer paso antes de get_current_state' tells the agent when to call this tool. It does not enumerate when not to use it or name alternative tools, but the intended workflow is clear.

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

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

Annotations already declare read-only and idempotent behavior, lowering the bar. The description adds that the response is a compact list of canonical URLs with optional entityId or resolveWith, and explicitly notes the absence of deep pagination. This is useful non-obvious context that goes beyond the 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 front-loaded with 'BUSCADOR: úsalo PRIMERO' and uses three dense sentences to convey purpose, return format, downstream usage, and limitations. Every sentence contributes value, with no filler or repetition.

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 2-parameter tool with no output schema, the description fully covers what the tool returns, how to interpret the result fields, which downstream tools to call, and what it cannot do. The workflow context is complete, and no critical operational detail is missing.

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 both query and limit well. The description reinforces that queries are free-form natural language but doesn't add new parameter-level details. A baseline of 3 is appropriate when the schema carries the parameter documentation burden.

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 states a specific verb and resource: a natural-language search over Alicante topics that returns canonical URLs. It explicitly differentiates the tool from siblings by naming it the entry point and listing concrete categories it covers. The mention of downstream tools like get_current_state and resolve_entity further clarifies its unique role.

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?

It explicitly instructs 'úsalo PRIMERO' for any natural-language query about Alicante, and frames the result as a decision aid for which 1–3 URLs to request next. It also states exclusions — no complete inventory and no deep pagination — which helps the agent avoid expecting unsupported behavior.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, so the safety profile is covered. The description adds useful context about AEMET official warnings and the breadth of data, but it does not disclose freshness, update cadence, or any limitations beyond the annotation coverage.

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 a single well-structured sentence that front-loads the core information and packs each listed data category with meaning. No filler or redundancy is present.

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 no-parameter, read-only tool with annotations covering behavior, the description is largely complete: it names all major output categories and the official warning source. It could be strengthened by clarifying how weather_now differs from beach_conditions, but nothing essential to invoking it correctly is missing.

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 tool has zero parameters, so there is no parameter burden for the description to carry. The baseline of 4 applies, and the description appropriately focuses on what the tool returns rather than input semantics.

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 enumerates the resource (current weather in Alicante) and the data categories it returns (temperature, wind, humidity, UV, forecast, sea state, AEMET warnings), so an agent can infer the tool's purpose. However, it lacks an explicit action verb and does not directly contrast itself with the overlapping sibling beach_conditions, which may also cover sea temperature and wave height.

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 gives no guidance on when to use this tool versus alternatives like beach_conditions or search_alicante. An agent must infer that weather_now is the right choice for general weather plus official warnings, which is not ideal given the potential overlap with beach_conditions.

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

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds useful context by specifying that results include 'eventos publicados' and cinema sessions with time and room, but it does not explain default behavior, such as what happens when no date is supplied, or pagination/result-shape details.

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 a single, efficient sentence that front-loads the core purpose ('Agenda de actividades y cine en Alicante') and then gives the concrete scope and result contents. There is no redundant or filler wording.

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 relatively simple, read-only tool with 100% schema coverage and strong annotations, the description is mostly complete. The only meaningful gap is the lack of explicit default behavior when no date is provided, which an agent might need to know when calling 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 parameters are already fully documented. The description adds slight semantic value by tying 'fecha' and 'búsqueda' to the date and query parameters, but it does not clarify interactions between parameters, defaults, or how 'limit' behaves beyond the schema definition.

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 identifies the tool as an agenda/activity finder for Alicante, covering both published events and cinema sessions with time and room. It is specific about the resource (activities and cinema in Alicante) and the two search modes (date or query), though it does not explicitly contrast itself with sibling tools like search_alicante.

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 implies the tool should be used when looking for activities or cinema in Alicante by a specific date or keyword, but it does not state when not to use it or name an alternative. Sibling tools like search_alicante, find_food, or find_place suggest alternatives exist, but no routing guidance is provided.

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