beyourspace data APIs

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

The description goes beyond the readOnly/idempotent annotations by disclosing concrete processing behavior: it validates numeric days, correct URLs, non-empty subjects, and duplicate removal. It also transparently states the price and payment mechanism (x402 with USDC on Base), which is valuable operational context not present in 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 short and front-loaded with the core action and expected output. However, the pricing information is stated twice in slightly different formats ('0,02 $ por petición' and 'Precio: 0.02 USD por llamada'), which is redundant and slightly reduces conciseness.

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 single-parameter conversion tool with no output schema, the description covers the input (CSV with header, max 1 MB), the output (validated JSON), and the cost. It does not specify the exact required CSV columns, but the validation hints ('días', 'URLs', 'asuntos') give enough guidance for an agent to understand the expected structure.

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 is minimal (one 'csv' parameter, 100% coverage), so the baseline is 3. The description adds meaningful context by specifying that the CSV represents an onboarding sequence and by implying expected fields ('días numéricos, URLs correctas, asuntos no vacíos'), which helps the agent understand what kind of CSV content is valid.

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: send a CSV with an onboarding sequence and receive clean, ordered, validated JSON. The title reinforces the resource ('onboarding email') and output ('JSON listo para importar'), making the tool's purpose distinct from sibling tools focused on requirements, changelogs, geocoding, or backlog tasks.

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: use this tool when you have an onboarding sequence in CSV and want a normalized JSON version. However, there is no explicit when-to-use or when-not-to-use guidance, nor any named alternative among the sibling tools, so the agent must infer the appropriate 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 convey readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful context beyond those annotations: the result is normalized JSON for ATS/agent/interview workflows and the call has a specific price. It does not contradict 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 short sentences with the core transformation and output shape front-loaded. The price line is the only secondary detail but is decision-relevant for a paid tool. There is no filler or redundant restatement.

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?

The tool is simple and the annotations plus schema cover safety and input limits, but there is no output schema and the description only vaguely promises 'JSON listo para ATS...' without specifying the normalized structure. It also leaves the boundary with normalizar-requisitos-csv unresolved, so an agent selecting among siblings is left guessing.

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% for the single csv parameter, including the required header and the 1 MB limit, so the schema already carries the parameter burden. The description only adds the general semantic that the CSV contains extracted job-offer requirements; this is marginal but not misleading.

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 has a specific verb ('Normaliza') and resource ('requisitos extraídos de ofertas laborales') and states the output format ('JSON listo para ATS, agentes y flujos de preparación de entrevistas'). However, it overlaps heavily with the sibling normalizar-requisitos-csv and does not explain how this tool differs from that one, so it is clear but not differentiating.

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: the tool should be used on requirements already extracted from job offers, not for the extraction itself. However, there is no explicit guidance about when to choose this over normalizar-requisitos-csv or extraer-requisitos-oferta, and no exclusions or alternative routing 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 declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false, so the description is not solely responsible for safety. It adds behavioral context by specifying the output format (CSV), the grouping/sorting logic, the input size limit, and the monetary cost per call. It does not contradict 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 entire description is a single, front-loaded sentence that states the action, input, output, and a key transformation, followed by a separate pricing note. No filler or redundant content.

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 with one input parameter and no output schema, the description covers the essential behavior: expected input type, output format (CSV), and processing logic. It lacks details on CSV columns and error handling, but these are minor for a tool this simple, given the annotations also cover safety.

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 describes 'data' as 'JSON de entrada (máx. 1 MB)'. The description elaborates that this JSON is a usage export from an LLM API, adding semantic meaning that the schema alone lacks. With 100% schema coverage, this is a meaningful bonus, though it still does not specify the JSON structure.

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 receives a JSON export of LLM API usage and returns a CSV of requests that missed cache, grouped by prefix and sorted by cost. This distinguishes it from all sibling tools, which appear unrelated (e.g., 'leer-pagina-markdown', 'indicador-eurostat').

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 when to use: when a user has a JSON usage export and wants to identify uncached prompts. However, it does not explicitly state when NOT to use it or compare with alternative tools, so it leaves the agent to infer the appropriate 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 readOnly, idempotent, non-destructive and open-world behavior. The description adds valuable cost context (0.02 USD via x402) and clarifies the transformation into structured output, so the agent understands the economic and functional behavior. No annotation contradiction.

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 purposeful sentences: the first states behavior and output, the second states cost/payment method. No filler, 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?

For a one-parameter, read-only tool, the description plus schema and annotations is nearly complete. It states the input, the output nature, and the cost, though it does not detail the exact output fields or formats; with no output schema, a slightly richer return specification would make it fully 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 covers the only parameter 100% with the description 'Texto libre, sin datos personales', so the schema does the heavy lifting. The tool description repeats no parameter details but does not need to; 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?

The description names the exact operation ('Convierte notas de versión') and the resource (changelog/release notes) and states the output shape (structured list of versions, changes, types). It is clearly distinct from sibling extraction tools, though it does not explicitly name any alternative.

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 a use context ('para alimentar agentes de documentación o seguimiento técnico') that implies when the tool is relevant, but it provides no explicit when-not-to-use guidance or comparison with sibling tools such as extraer-requisitos-oferta or normalizar-requisitos-csv.

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, idempotent, open-world, and non-destructive behavior. The description adds useful context beyond the annotations by disclosing the cost per call (0.02 USD via x402/USDC) and by specifying that extraction is conditional ('cuando aparecen') for price, which gives the agent a clearer expectation of the tool's behavior.

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 front-loaded: it states the conversion purpose, enumerates the extracted attributes, and adds the pricing detail in a single additional sentence. Every sentence earns its place with no redundant 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 simple one-parameter read-only tool with no output schema, the description provides sufficient context: what input to provide, what attributes to expect in the output, and the cost. It is complete enough for an agent to select and invoke 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 coverage is 100% for the single 'text' parameter, so the schema already documents it as free text without personal data. The description adds complementary semantics by clarifying that the text should be a product sheet or description, helping the agent understand what kind of input is expected.

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 converts a product sheet or description into structured attributes, listing the specific fields extracted: name, brand, characteristics, measurements, and price when present. This is a specific verb+resource combination and the product-focused scope distinguishes it from sibling extraction tools like extraer-changelog or extraer-requisitos-oferta.

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 use context is implied: the tool is appropriate when the input is a product sheet or product description. However, there is no explicit guidance about when to choose this tool over alternatives, no exclusions, and no mention of sibling tools, so the routing decision is left to inference.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, covering safety. The description adds the pricing per call and the intended downstream use (filtering by an agent), but does not elaborate on side effects, language, or output specifics. It does not contradict 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?

A single sentence delivers the core purpose, followed by a pricing note. It is front-loaded, free of filler, and each part adds distinct value (function, output elements, cost).

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 tool with no output schema, the description lists the extracted elements but does not describe the output structure (e.g., field names, JSON format). Pricing and input type are covered, but an agent might need more detail on how to consume the result. Still, it is reasonably complete for the tool's simplicity.

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 describes 'text' as free text without personal data, while the description adds that it must be a public job offer, enriching the semantic meaning. With 100% schema coverage, this additional context goes beyond the schema, though it does not specify format constraints.

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 it converts job offer text into structured requirements (mandatory/desirable, years, modality, location) for filtering, with a specific verb and resource. It does not explicitly differentiate from similar siblings like 'convierte-requisitos', but the specified output elements make its scope evident.

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?

No guidance is provided on when to use this tool versus alternatives, nor any exclusions or conditions. The description only states what it does and the pricing, leaving the agent to infer usage context from the name and 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 declare readOnlyHint=true and idempotentHint=true, so the description adds extra behavioral context without contradicting them: it discloses the lack of legal validity, the CC BY 4.0 attribution requirement, and the per-call price. This goes beyond what annotations alone provide.

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 dense sentence that front-loads the core conversion behavior and then adds essential caveats, attribution, and pricing. Every clause earns its place with no wasted words.

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?

The tool has no output schema and no parameter documentation, so the description must carry the full burden of guiding invocation. It provides purpose, legal notes, and pricing, but omits parameter semantics, return format, and example usage, leaving an agent without enough information to call the tool reliably.

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% and the description does not explain the 'direccion' or 'limite' parameters, their formats, or whether they are required. Although 'direccion' is inferable from the tool's purpose, 'limite' remains unexplained and no address format guidance is given.

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 ('Convierte'), a clear resource (Spanish addresses via CartoCiudad del IGN), and the expected outputs (coordinates, municipality, province, postal code). This clearly differentiates it from sibling tools, which are mostly generic converters or indicator-related 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 description implies usage for geocoding Spanish addresses and adds a caveat about legal validity, but it does not explicitly state when to choose this tool over alternatives or mention any exclusions. The intended context is inferable but not directly guided.

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, idempotentHint, and non-destructive behavior. The description goes beyond this by disclosing the per-call price in USD with x402 on Base, and by enumerating what the result contains: period, unit, whether it is an estimate, and the dataset citation. This is useful operational context that the annotations do not provide.

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 tightly scoped sentences with no filler. The first sentence front-loads the tool's purpose and result fields, and the second states the cost. Every part earns its place, and the structure is 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?

With no output schema, the description carries the burden of explaining both the return shape and how to invoke the tool. It does mention the return components and price, but it omits parameter value guidance and does not explicitly route the agent toward indicador-ine when Spanish national statistics are needed. This leaves a meaningful gap 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%, and the two parameters have no types, descriptions, or enums. The description broadly maps 'pais' to an EU country and 'indicador' to inflation or unemployment, but it does not specify accepted string values, codes, or formats. An agent still has to guess whether to pass 'ES' or 'España', and whether 'indicador' should be 'inflacion', 'IPCA', or another value.

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 identifies a specific data-retrieval resource: the latest Eurostat inflation (IPCA) or unemployment value for an EU country, and lists returned fields such as period, unit, estimation flag, and dataset citation. It is clear but phrased as a noun phrase rather than a verb, and it does not explicitly distinguish itself from the sibling tool indicador-ine, though 'según Eurostat' implies the difference.

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 is for EU-country Eurostat inflation/unemployment lookups, which gives the agent a reasonable context signal. However, it provides no explicit alternatives, exclusions, or guidance about when to prefer this tool over the closely related indicador-ine. The division of labor with that sibling is left to inference.

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

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 that the tool returns period, unit, and attribution, and that it costs 0.01 USD per call with x402. It does not disclose what happens if the serie is invalid or not found, or how the attribution requirement affects the response. The pricing disclosure is a useful behavioral addition beyond 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 sentences and front-loads the core function. The pricing sentence is arguably necessary for a paid tool. It is concise and every sentence adds information, though the pricing could be seen as secondary.

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 with one undocumented parameter, no output schema, and no usage guidance, the description is incomplete. An agent cannot reliably construct a valid 'serie' value from the description alone. The openWorldHint suggests the parameter accepts open-world values, but the description does not provide examples of valid serie identifiers or how to discover them. The pricing and attribution info are useful, but the core calling contract is underspecified.

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% and the only parameter 'serie' has an empty schema with no description. The description mentions example series (IPC, paro, población) but does not explain what format the serie parameter should take (e.g., INE series code, name, URL). With 0% coverage and no parameter documentation, the description must compensate, and it only partially does by giving examples of series topics.

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 latest published value of an INE series, with period, unit, and attribution. It names example series (IPC, unemployment, population), which helps an agent understand the resource. It doesn't explicitly distinguish itself from the sibling indicador-eurostat, but the INE vs Eurostat distinction is implicit in the name and description.

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 when to use it: when you need the latest INE data point. It does not explicitly state when not to use it or mention the sibling indicador-eurostat as the alternative for Eurostat data. The pricing note is context but not usage guidance. The lack of required parameters and openWorldHint suggest the agent may need to discover the serie parameter, but no guidance is given on how to find valid series identifiers.

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 readOnly, openWorld, idempotent, and non-destructive hints. The description adds valuable behavioral context: the restriction to 'página pública permitida' (allowed public pages), the transformation to 'contenido principal' (main content), and the cost of 0.01 USD per call with x402. These go beyond the annotations and inform the agent about practical constraints and pricing.

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 with no fluff. The primary purpose is front-loaded, and the pricing detail is neatly appended. Every sentence adds 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 simple tool with one parameter, full schema coverage, and annotations covering safety, the description is complete. It includes the allowed-page restriction, the main-content extraction, and the cost. No output schema exists, so no return-format explanation is required. 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 schema already documents the url parameter (100% coverage) as a public HTTPS URL. The description adds the 'permitida' qualifier, which is more about tool behavior than parameter semantics. It does not add format or syntax details beyond the schema, so the baseline 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 states the action (downloads a public page) and the output (main content in Markdown), with a specific verb and resource. It distinguishes itself from sibling tools that perform specific extractions (e.g., extraer-changelog) by being a generic page-to-Markdown converter, though it does not explicitly name those alternatives.

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 context (so an agent can process without browsing HTML) but offers no explicit guidance on when to use this tool versus the many sibling extraction tools. It does not mention any exclusions or alternative tools, leaving the 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 cover read-only, idempotent, open-world, and non-destructive behavior. The description adds that the output is clean, consistent JSON and discloses a per-call cost via x402, which is useful operational context beyond the structured 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, well-structured sentence that front-loads the action, explains the purpose, and adds the pricing detail without fluff. 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?

For a one-parameter conversion tool with full schema coverage and strong safety annotations, the description provides sufficient context: input type, output format, use case, and cost. No output schema exists, but the promised JSON output is 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?

The single `csv` parameter is fully described in the schema ('CSV con cabecera (máx. 1 MB)'). The description adds that the CSV should come from CI jobs and that the result will be JSON, enriching the parameter's meaning without redundancy.

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: it converts CI job CSV exports into normalized JSON for detecting slow builds, cache failures, and repeated steps. This clearly differentiates it from siblings like normalizar-requisitos-csv, which target a different CSV domain.

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 a clear use context: use it when you have CI job CSV exports and want consistent JSON for build-performance analysis. It does not explicitly name alternatives or exclusions, but the intended scenario is obvious enough.

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, idempotentHint y destructiveHint. La descripción añade comportamiento de procesamiento (limpieza, deduplicación, normalización), el formato de salida JSON y el coste de 0.01 USD, lo que da contexto útil más allá de las anotaciones. No contradice 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?

La descripción es breve y directa: la primera frase define función y salida, la segunda informa del coste. No hay relleno, y la información clave está al inicio.

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 con un único parámetro y sin output-schema, la descripción cubre la salida esperada (JSON con section, text y priority), la operación realizada y el coste. Faltan detalles como el formato exacto de las columnas de entrada o la estrategia de deduplicación, pero no impiden invocarla correctamente en el caso común.

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 schema ya documenta completamente el único parámetro 'csv' con descripción 'CSV con cabecera (máx. 1 MB)', por lo que la cobertura es del 100%. La descripción no añade detalles adicionales sobre el formato esperado del CSV ni sobre cómo se interpreta el parámetro, manteniéndose en 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 usa verbos concretos ('Limpia', 'elimina', 'devuelve') sobre un recurso específico ('CSV de requisitos') y declara el formato de salida (JSON con columnas section, text y priority). Diferencia claramente la herramienta de las hermanas orientadas a extraer o convertir requisitos.

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?

No explica cuándo usar esta herramienta frente a alternativas como extraer-requisitos-oferta o convierte-requisitos. Solo se infiere un caso de uso a partir del propósito, pero no hay criterios de exclusión, prerequisitos ni orientación sobre cuándo no usarla.

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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it clarifies the transformation nature (input CSV → output JSON), specifies the output fields, and discloses the cost/payment requirement (0.02 USD per call via x402 on Base). This gives the agent important operational information not present in the structured 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?

The description is two sentences with zero fluff. The first sentence front-loads the core purpose, input, output, and downstream use; the second briefly states pricing and payment method. Every word earns its place, and the structure is 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 one-parameter tool without an output schema, the description is quite complete: it states the input type, output format, and output fields, and mentions the cost and payment method. The annotations cover the operational safety (read-only, idempotent). The only minor omission is the lack of an explicit example or error-handling details, but these are not critical for a straightforward transformation 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?

The schema already covers the 'csv' parameter with 'CSV con cabecera (máx. 1 MB)', but the description adds value by specifying that the CSV contains SaaS onboarding events and by describing the output properties (standard account IDs, event names, dates, plans). This helps the agent understand what input data is appropriate and what the output will look like, going beyond the schema's basic size/header note.

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 ('Convert'), the resource ('inconsistent SaaS onboarding event CSV files'), and the output ('clean JSON with standard account IDs, event names, dates, and plans for downstream email automation'). It clearly distinguishes itself from sibling tools like 'convierte-onboarding' and 'normalizar-requisitos-csv' by specifying the SaaS onboarding context and the email automation downstream 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?

The description implies when to use the tool (when you have inconsistent SaaS onboarding event CSVs and need clean JSON for email workflows), but it does not explicitly state when not to use it or point to alternatives. Sibling names hint at alternatives, but the description itself offers no direct comparison or exclusion criteria.

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 a rich safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description's burden is lower. It adds useful context beyond the schema — the output is 'limpio y ordenado por prioridad' and the call costs 0.01 USD via x402 — but does not disclose other behavioral traits such as failure modes, rate limits, or how priority is determined.

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 short sentences with the core transformation front-loaded and the cost detail second. No wasted words; the pricing sentence earns its place for cost-aware tool selection.

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 single-parameter tool with rich annotations and no output schema, the description covers the input domain, the output form (JSON backlog ordered by priority, agent-consumable), and cost. It does not describe the output structure in detail, which matters more because no output schema exists, but the simplicity of the tool limits the 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% for the single 'csv' parameter, but the description adds meaning by specifying the expected content ('experimentos de adquisición'), which the schema's generic 'CSV con cabecera' does not convey. This helps an agent prepare correct input beyond what the schema alone documents.

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 transformation — receiving an acquisition-experiment CSV and returning a clean, priority-ordered JSON backlog for agent consumption. The domain and output format are specific enough to narrow scope, but it does not explicitly differentiate from the near-sibling 'prioriza-backlog', so an agent still must infer the distinction from scope rather than being told.

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 rather than explicit: an agent can infer this tool is for turning acquisition-experiment CSVs into an ordered JSON backlog. However, there is no when-to-use versus when-not-to-use guidance, and no mention of the overlapping siblings 'prioriza-backlog' or 'normalizar-requisitos-csv', leaving the routing decision 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it is a paid API (0.02 USD per call) with a specific payment method (x402/USDC on Base), and it normalizes input into a structured JSON backlog. This goes beyond the annotations and helps the agent understand cost and output behavior.

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, information-dense sentence that front-loads the core purpose and includes pricing. It is concise and every part adds value, though it could be slightly more structured with a separate sentence for pricing. Overall, it is efficient and well-organized.

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 single-parameter tool with full schema coverage and read-only/idempotent annotations, the description is largely complete. It explains the input (CSV), the output (prioritized JSON backlog with specific fields), and the cost. The only minor gap is not specifying the exact CSV format or headers, but the schema already says 'CSV con cabecera (máx. 1 MB)' and the description lists the output fields, which implies the expected input structure.

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 single 'csv' parameter is already documented in the schema. The description adds context about what the CSV contains (candidates for SaaS acquisition experiments) and the output fields, but it does not add syntax, format, or example details beyond the schema. 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 states a specific verb ('normaliza'), a clear resource ('candidatos de experimentos de adquisición SaaS'), and the output format ('backlog JSON ordenado por prioridad'). It also lists the fields included, which distinguishes it from generic backlog tools. The sibling 'ordenar-backlog-experimentos' is close, but this description's emphasis on normalizing candidates and the paid API nature helps differentiate it.

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 usage: it takes CSV candidates and returns a prioritized JSON backlog. It does not explicitly state when to use this tool versus 'ordenar-backlog-experimentos' or other sibling tools, nor does it mention exclusions or alternatives. The pricing and x402 payment detail provide some context, but no explicit when-to-use 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 provide readOnlyHint, idlempotentHint, and non-destructive semantics, so the description doesn't need to restate safety. It adds real behavioral context by specifying exact output fields, naming OSV.dev as the vulnerability source, noting sources for advisories, and stating the paid pricing model. 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?

Two short sentences with the core data scope front-loaded and only the pricing note at the end. Every sentence carries needed information; there is 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 single-parameter tool with no output schema, the description gives a clear picture of returned data and benefits from safe annotations. However, it omits parameter format, requiredness, and selection criteria, leaving a significiant gap in practical usability.

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% and the only parameter 'paquete' is an empty schema with no required flag. The description says it concerns an npm package version but does not specify the expected format, such as 'operator@version', nor whether the parameter is mandatory. The agent is left guessing about how to construct the call.

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 (an npm package version) and enumerates the results: license, repository, dependency count, and known vulnerabilities with sources. It is specific and useful, but uses a noun phrase rather than an explicit verb and does not contrast with 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 description implies the tool is for investigating a specific npm package version's risk profile, but it gives no explicit conditions for when to use this tool versus alternatives, and no exclusions. The mention of 'a concrete version' offers some context, but not full routing guidance.

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