El Pujante — Subastas públicas de España

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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is established. The description adds valuable behavioral nuance beyond that: 'Devuelve siempre solo subastas activas' and the caveat that cargas_ratio_max 'solo poda las subastas con cargas numéricas'. This is exactly the kind of non-obvious behavior an agent needs, and nothing contradicts 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 a one-line purpose, followed by a compact bullet list giving each parameter just enough semantics, and a short paragraph for location exclusions and the always-active behavior. Every sentence earns its place; there is no filler or redundancy despite covering a 15-parameter tool.

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 15-parameter search tool with no required arguments and no output schema, the description covers the essential invocation context: optional filters, value examples, location semantics, the no-free-text limitation, and the always-active-auction guarantee. It is slightly incomplete on the omitted price/m2 parameters and does not describe the result shape, but that is minor for a list-style search tool with sibling tools for details.

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 0%, so the description carries the burden and does so well: it explains uso, bien_subtipo, tipo_subasta, descuento_min, dias_max, cargas_ratio_max, orden, limit, and the three location filters with examples, units, and constraints. It never mentions precio_min/precio_max/m2_min/m2_max, although these are inferable from their names, so it is not fully complete.

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 first sentence names a specific verb and resource: 'Busca inmuebles en subasta pública activa en España (BOE, AEAT y Seguridad Social)'. This clearly identifies the tool as a search over active public-auction properties in Spain from concrete sources, which is distinct enough from siblings like detalle_inmueble or comparar_inmuebles even without naming them.

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 clear context: all filters are optional. It also explicitly states what the tool does not do ('No hay búsqueda por texto libre ni parámetro de ubicación genérico'), redirecting to municipio/provincia/codigo_postal. However, it never names sibling tools or states when to use an alternative, so it misses the explicit when-not guidance required for 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the 2-to-5 item constraint and the fact that it returns complete property sheets, which is useful behavioral context. It does not mention edge cases such as invalid counts or response format, but there is no contradiction with 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 a single, short sentence with no filler. The key constraint (2 to 5 properties) and the purpose (side-by-side comparison) are front-loaded, making it efficient and easy to scan.

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 tool with one parameter and rich annotations, the description covers the core behavior and the count constraint adequately. However, it lacks explicit sibling differentiation and does not describe behavior for out-of-range input, which leaves some gaps. It is minimally viable but not comprehensive.

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 0%, so the description must compensate for the undocumented bien_ids parameter. It partially does so by indicating the array should contain 2 to 5 properties, but it does not explain that bien_ids are property identifiers or how to obtain them. The schema's title 'Bien Ids' and array-of-integers type are self-explanatory, so the main added value is the count constraint.

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 complete property cards for 2 to 5 properties for side-by-side comparison. This conveys the operation and resource, and the comparison framing differentiates it from single-property tools like detalle_inmueble. The main clause lacks an explicit verb, but the intent is 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?

Usage is implied by the '2 a 5 inmuebles' constraint and the comparison purpose, which suggests using it when a user wants to compare multiple specific properties. However, it does not explicitly state when to prefer this tool over inmuebles_similares or detalle_inmueble, nor does it provide any exclusions or alternative routing.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds meaningful behavior beyond that by listing what is included in the estimate and explaining that `precio` defaults to the subasta value. There is no contradiction with 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 two compact sentences with no filler. The first sentence states the purpose and the full list of cost components, and the second clarifies the key parameter behavior. Every clause contributes value.

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 calculator tool backed by strong annotations, the description adequately covers purpose, parameter semantics, and estimation scope. The main gap is the absence of an output schema or an explicit statement of the return format/currency, but the information provided is sufficient for selecting and calling the tool correctly.

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 0%, so the description must compensate for missing parameter documentation. It clearly explains `precio` as the hypothetical remate and its default behavior, but it does not explain the required `bien_id`, leaving that parameter to be inferred from context.

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 operation—estimating the real cost of adjudicating a property—and breaks down the cost components (precio + ITP + notaría + registro + cargas subrogables). This clearly separates it from sibling tools like detalle_inmueble or resumen_riesgo, which address different questions.

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: whenever an agent needs the total acquisition cost of a property including taxes and fees. However, there is no explicit mention of when to choose this tool over the siblings, nor any exclusions, so the agent must infer the context.

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, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds scoping context (by `bien_id`, complete record) but no additional behavioral traits such as response envelope, error cases, or rate limits. No contradiction with 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?

One compact, front-loaded sentence that states the action, the key parameter, and the result contents. Every word earns its place; there is no repetition of schema fields or annotation values.

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 one required parameter, safety annotations, and no output schema, the description gives enough to invoke the tool correctly and know what to expect: the key and the main content categories. It could add response envelope or error details, but for a simple read-only lookup these are not critical.

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 0%, so the description must carry the semantic meaning. It explains that `bien_id` is the property identifier used to select the record, which is meaningful beyond the raw schema type. For a single obvious required parameter, this is sufficient.

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 resource and action ('Ficha completa de un inmueble en subasta') and identifies `bien_id` as the selector. The listed contents (valores, fechas, cargas, datos catastrales, coordenadas, URL oficial) clearly distinguish it from the search, comparison, risk, and stats siblings.

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 is implied clearly: call this to get the full record for a specific property by its ID. However, the description does not explicitly state when not to use it or name alternatives like buscar_inmuebles or comparar_inmuebles as better fits for other needs.

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 the tool read-only, idempotent, and non-destructive. The description adds a concrete filtering behavior: only active auctions, with OR-ed criteria (postal code, or use + province + price band). It does not describe return format or edge cases, but the annotation coverage makes this acceptable.

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?

A single compact sentence front-loads the resource (active auctions) and then gives the matching conditions. There is no filler or redundant repetition of the tool name.

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 tool with safety annotations, the description covers the core behavior and matching criteria. It leaves the response shape and the effect of limit implicit, but the schema provides the limit default and the purpose is clear enough for correct invocation.

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 0%, so the description must compensate. It implies bien_id is the reference property ('la dada') but never names or explains limit, and the price criterion is not tied to a parameter. This is only partial compensation for the missing schema-based parameter documentation.

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 the operation as returning active auctions similar to a given property, with explicit similarity rules (same postal code, or same use in the same province with ±20% price). This clearly distinguishes it from sibling search/compare tools by focusing on a reference property and similarity matching.

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 this tool is for 'find similar properties/auctions to this one' requests, and the 'a la dada' wording signals a prerequisite bien_id. However, it does not explicitly mention when to prefer this over buscar_inmuebles or comparar_inmuebles, nor any exclusion 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, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds behavioral output context by enumerating the types of alerts (cargas elevadas, deuda subsistente TGSS, vivienda habitual) and positive signals, which is valuable because there is no output schema. It does not describe return format or data source, but no contradiction exists.

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 front-loaded sentence plus a short imperative, and every phrase carries distinct information: what the tool returns, examples of content, and when to use it. There is 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 simple one-parameter read-only tool, annotations cover the safety semantics and the description covers purpose, content categories, and a usage rule. However, the required bien_id parameter is left under-specified and there is no output schema to compensate. The description is useful but has a genuine gap around how to identify the target.

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 only required parameter, bien_id, is not explained in the description, and the schema provides 0% property-description coverage. The description talks about 'subasta' while the parameter is 'bien_id,' leaving the relationship between the property and the auction unresolved. With a single required parameter at 0% coverage, the description needed to explicitly state that bien_id identifies the property whose auction risk is being summarized.

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 provides risk and opportunity indicators for an auction, including concrete alert examples and positive signals. This distinguishes it from siblings like detalle_inmueble, which would cover general property detail, and from comparar_inmuebles or costes_totales. Although there is no explicit verb, the function is 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 gives an explicit timing rule: 'Consultar SIEMPRE antes de recomendar una subasta,' which tells the agent when this tool must be invoked. It does not name alternatives or exclusion conditions, but the mandatory-use context is clear enough for routing.

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 safe read-only/idempotent behavior, and the description does not contradict them. It adds that the view is global and aggregate, but provides no deeper behavioral context such as freshness, units, or scope caveats.

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?

A single, front-loaded sentence conveys the tool's whole value proposition without filler. Every phrase names a distinct output category.

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 param-free aggregate tool with no output schema, the description is nearly complete: it lists all returned dimensions. Minor gaps such as currency, units, or response shape keep it from a 5.

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?

With zero parameters, there is no parameter ambiguity and schema coverage is trivially 100%. The description still helps by enumerating what dimensions the stats cover, so the agent knows what the no-arg call returns.

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 concrete deliverable: global inventory figures with explicit breakdowns (active auctions by source/province/type, average prices, enrichment coverage). This content profile separates it from siblings like detalle_inmueble or costes_totales.

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 only implied: an agent would infer to call it when it needs aggregate inventory statistics. The description never states when not to use it or names alternatives, so routing versus costes_totales or resumen_riesgo is left to the agent.

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