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

No annotations are provided, so the description carries the burden. It discloses the output format (XML SOAP), the SII version (v3.0, April 2024), and supported TipoComunicacion values (A0/A1/A4). It does not disclose whether the tool validates the XML, whether it persists anything, or what the output schema contains, but the description does add meaningful behavioral context beyond the schema.

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: it states the core purpose in the first sentence, then adds version and communication-type details. Every sentence earns its place, though the Spanish phrasing is slightly dense and could be clearer about the build-only scope.

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 an output schema and 100% parameter coverage, so the description need not explain return values. However, with no annotations and a complex domain (SII XML/SOAP), the description could usefully mention whether the record is validated, whether it handles signing, and how it relates to submission tools. It is adequate but leaves the agent to infer the build-vs-submit boundary.

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 four parameters. The description adds context for record_type ('issued' vs 'received') and communication_type (A0/A1/A4), but these are also present in the schema. The description does not add meaning beyond the schema for invoice or clave_regimen, so a baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool builds an AEAT SII XML record in SOAP format, distinguishing between issued (FacturaExpedida) and received (FacturaRecibida) invoices, and lists supported communication types. It is specific about the resource and format, though it does not explicitly differentiate from siblings like es__generate_sii_correction or es__submit_sii_batch; the verb 'build' and XML/SOAP focus make the core purpose clear.

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 is for constructing SII records, not submitting them, and it names the supported communication types. However, it does not explicitly state when to use this tool versus alternatives such as es__submit_sii_batch (submission) or es__generate_sii_correction (corrections). The context is clear enough for an agent to infer the build-vs-submit distinction, but explicit when/when-not guidance is missing.

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?

Sin anotaciones, la descripción aporta algo de transparencia: crea un registro de anulación específico (TipoHuella=01) y depende del encadenamiento con la huella actual. No menciona efectos secundarios, permisos ni si el registro se envía a AEAT, pero 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 breves y sin relleno; la información principal aparece al inicio y la frase secundaria aporta contexto de encadenamiento.

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?

Dispone de esquema de entrada completo y esquema de salida, y la descripción cubre la operación y el contexto de cadena. Aun así, falta explicitar la relación con las herramientas hermanas de generación/envío y posibles condiciones previas para anular un registro.

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 cobertura del esquema es del 100%, por lo que la descripción no necesita documentar cada parámetro; 'Encadenado a la secuencia de huellas actual' refuerza el significado de previous_hash y previous_*. No añade formato o reglas de validación adicionales.

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?

El texto especifica un verbo concreto ('Genera') y el recurso exacto ('registro de anulacion VERI*FACTU') con el tipo huella. Esto permite distinguir la operación de anulación de otras herramientas del mismo dominio, aunque no nombra explícitamente a los hermanos.

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 'Encadenado a la secuencia de huellas actual' da contexto de uso: debe ejecutarse tras un registro previo en la cadena. No hay una declaración explícita de cuándo preferir esta herramienta frente a es__generate_verifactu_record ni de 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?

No annotations are provided, so the description carries the burden. It discloses that the tool applies mutual exclusion logic from RD 254/2025, which is a useful behavioral trait. However, it doesn't describe what happens on edge cases (e.g., invalid province code, zero turnover, conflicting inputs), nor does it mention whether the tool returns a single regime or a list. The description adds some behavioral context but not comprehensive.

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 with the main purpose. The first sentence states the core function, and the second adds the legal logic. It's efficient, though the line break and formatting could be slightly cleaner. 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 an output schema (not shown but indicated), which likely explains return values. The description covers the inputs and the decision logic. It doesn't mention error handling or edge cases, but for a determination/check tool with a clear purpose and full schema coverage, this is reasonably complete. A note on what the output looks like would make it 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?

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds context by explaining how the parameters are used (volume, province code, SII enrollment) to determine the regime, but it doesn't add new semantic details beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: determining the applicable e-invoicing regime (VERI*FACTU, SII, TicketBAI, NaTicket) based on turnover, province code, and SII enrollment. It also references the specific legal logic (Real Decreto 254/2025), which distinguishes it from sibling tools like es__detect_regional_regime or es__generate_b2b_einvoice_es.

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 this tool: when you need to determine which e-invoicing regime applies based on business parameters. It doesn't explicitly state when NOT to use it or name alternatives, but the context of sibling tools (e.g., es__detect_regional_regime) and the specific inputs make the usage context fairly clear. A brief mention of alternatives would push this to 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?

No hay anotaciones, y la descripción aporta que la herramienta devuelve un valor dentro de un conjunto finito y que depende de la provincia y de la inscripción en SII. Sin embargo, no dice explícitamente si es solo de lectura, si hace llamadas externas o si requiere autenticación/precondiciones. Aunque 'Detecta' sugiere una operación de consulta, el margen de mejora está en declarar esa naturaleza read-only.

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: tres frases, cada una con una función clara (qué hace, de dónde sale, cuándo usarla). No hay relleno y la información importante está al principio.

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 solo 2 parámetros, schema descrito al 100% y output schema declarado, la descripción proporciona lo esencial: propósito, entradas básicas, valores de salida y directriz de uso. No es necesario ampliar formato de retorno porque el output schema lo cubre.

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 input-schema ya documenta el 100% de los parámetros: province_code con formato y ejemplos, y enrolled_in_sii con valor por defecto. La descripción agrega el propósito global y los valores de salida, pero no explica explícitamente cómo enrolled_in_sii=true modifica el resultado (p. ej., cuándo aparece VERIFACTU+SII), por lo que se queda en la referencia mínima.

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 comienza con un verbo específico ('Detecta el régimen de facturación electrónica aplicable') y define el recurso (código de provincia INE) y los posibles resultados (VERIFACTU, TICKETBAI, NATICKET, VERIFACTU+SII). Esto la distingue de las herramientas hermanas de generación, validación, envío y consulta, al presentarla como una etapa previa de decisión.

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 'Usar siempre antes de llamar a cualquier otra herramienta de este servidor' es una pauta de uso explícita y jerárquica. No hay ambigüedad sobre cuándo invocarla: siempre antes de cualquier otra herramienta, lo cual compensa la ausencia de una sección de alternativas.

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?

No hay anotaciones, por lo que la descripción debe asumir toda la carga de transparencia. Solo menciona la generación conforme a normas, pero no informa sobre efectos secundarios, si valida el contenido, si firma el documento, o si realiza alguna comprobación de obligatoriedad. Para una herramienta de generación compleja, esto es insuficiente.

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 primera frase es directa y va al grano. La segunda frase aporta contexto regulatorio útil aunque no imprescindible para la invocación; el conjunto es breve, estructurado y no contiene relleno excesivo.

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?

La herramienta tiene un esquema complejo con un objeto 'invoice' sin propiedades definidas y no hay anotaciones. La descripción no explica cómo estructurar los datos de la factura, si el resultado requiere validación o firma posterior, ni cómo se relaciona con las herramientas hermanas de envío a AEAT/FACE. La existencia de output schema no compensa la falta de orientación práctica.

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 cobertura del esquema es del 100%, por lo que la línea base es 3. El parámetro 'format' tiene descripción suficiente ('ubl' por defecto o 'facturae'), pero 'invoice' solo se describe como 'Datos de la factura' y no se detalla su estructura interna ni campos obligatorios, pese a ser un objeto anidado con additionalProperties.

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 indica claramente el verbo ('Genera'), el recurso ('factura B2B') y los formatos de salida ('UBL 2.1 o Facturae 3.2.2'), además de la norma aplicable (EN 16931). Aunque no diferencia explícitamente de herramientas hermanas como generate_facturae_xml, el propósito es claro y accionable.

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 se indica cuándo usar esta herramienta frente a alternativas ni cuándo no usarla. La referencia a la Ley 18/2022 y al RD 238/2026 aporta contexto normativo, pero no orienta al agente sobre la elección entre esta herramienta y las relacionadas con Facturae, Verifactu o SII.

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?

No annotations are provided, so the description carries the full transparency burden. It does disclose the most important behavioral trait—the generated document is unsigned and requires a separate signing step. However, it does not address whether any state changes, permissions, or side effects exist beyond that.

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 with zero waste: the first explains what is generated and for whom, the second provides the critical caveat and next-step tool. Essential information 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 rich input schema, the output schema, and the clear naming of the signing tool, the description provides enough context for correct invocation. It could also have pointed to es__submit_to_face as the final B2G submission step, but the signing step is enough as the immediate next action.

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 has 100% description coverage, so each parameter already carries semantic meaning (e.g., tax_type distinguishes IVA/IGIC/IPSI, irpf_rate, recargo_equivalencia). The main description adds little parameter-level detail, so a 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?

States a specific verb and deliverable: generates a Facturae 3.2.2 XML for B2G submission to the FACe portal. This clearly distinguishes it from B2B, Verifactu, and SII 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 explicitly says the XML is for B2G/FACe and names es__sign_facturae_xades as the next step, giving the agent a direct call chain. It does not explicitly list when not to use it, but the B2G/FACe and unsigned-signing guidance is enough to disambiguate from the other 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?

No annotations are provided, so the description carries the burden. It discloses the output format (PNG in base64) and the encoded URL, which is useful. However, it does not mention whether the QR is generated locally, whether any network call is made, or what the output schema contains beyond the base64 PNG.

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 with the core purpose and regulation. The second sentence adds the encoded URL context. It is slightly truncated (ends with '...'), which is a minor structural flaw, but overall it is efficient and focused.

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 an output schema and 100% parameter coverage, so the description need not explain return values or parameters in depth. However, with no annotations, the description could have clarified whether the QR generation is offline or calls AEAT, and how the output is returned. The core purpose is clear, but behavioral context is thin.

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 parameters. The description adds the context that these fields map to the AEAT QR URL, but it does not add meaning beyond the schema's field descriptions. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: generating the mandatory VERI*FACTU QR code as a base64 PNG, and cites the specific regulation (HAC/1177/2024 Art. 10). It also names the encoded AEAT verification URL, which distinguishes it from sibling tools that handle records, submission, or status queries.

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 generating the QR code for a specific invoice, but it does not explicitly state when to use it versus alternatives like es__generate_verifactu_record or es__submit_verifactu_to_aeat. The regulatory citation and QR-specific wording provide context, but no explicit when/when-not guidance is given.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states only that it generates a record and references the original invoice via IDFactura; it does not indicate side effects, whether the record is submitted, or if validation occurs. This is minimal for a statutory tax tool.

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 two-sentence description is entirely focused: first sentence states the action, the second adds the key referencing detail. No filler, irrelevant info, or redundant restatement 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?

Given the output schema exists and the input schema has 100% coverage with useful descriptions, the description adds the essential missing detail (IDFactura reference). However, it does not clarify the relationship with the submission workflow or the expected format of the returned correction record, which would slightly improve completeness.

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%, but the description adds meaningful semantics not present in the schema: 'Referencia la factura original mediante IDFactura' tells the agent that original_invoice must be identified by IDFactura. This is genuine extra information about the original_invoice 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 the tool generates an SII correction record (A1 modification) or cancellation (A4), which is a specific verb and resource. It also references the original invoice via IDFactura, distinguishing it from sibling tools that generate Verifactu or build regular SII invoice records.

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 explicit guidance is given on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or references to sibling tools like es__build_sii_invoice_record or es__submit_sii_batch. The only usage hint is the schema note about omitting corrected_invoice for A4, which is not in the description.

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?

With no annotations, the description carries the full burden. It discloses the core behavior: generating a record, returning XML and a fingerprint for chaining, and notes the prerequisite check. It doesn't mention side effects or error conditions, but for a generation tool these are not critical and the output schema covers return 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 three sentences, each earning its place: the main action, the output, and a prerequisite call. It is front-loaded with the most important information and contains no fluff.

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 tool's complexity (11 parameters, nested invoice object, output schema), the description covers the essential aspects: what it generates, what it returns, and the prerequisite check. The output schema and parameter schema handle detailed field documentation, so nothing critical 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 baseline is 3. The description adds value by explaining the chaining concept ('encadenar con el siguiente registro'), which clarifies the purpose of the previous_* parameters. It also contextualizes the Huella, aiding understanding of the hash 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 the tool generates a VERI*FACTU invoice record with SHA-256 chaining, referencing the specific regulation. It mentions returning XML and the fingerprint, distinguishing it from validation, submission, and cancellation siblings by focusing on generation.

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 calling es__detect_regional_regime first to confirm the regime is VERIFACTU, which is a clear precondition. It does not explicitly name alternative tools for other regimes, but the specificity to VERI*FACTU and the prerequisite make the usage context 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?

No annotations are present, so the description must carry behavioral disclosure. It only says it returns values and warns that the data may change due to later legislation. It does not state whether the operation is read-only, whether it has side effects, error semantics, rate limits, or the reliability conditions under which it might fail. The warning about future legislative changes is useful but does not fulfill the full transparency burden.

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, front-loaded with the main purpose and a compliance caveat. No wasted words. It loses one point because the core term 'sistema operativo' is unclear, which could have been replaced with a more precise phrase in the same space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the return structure is covered, but the description is too thin for a regulatory determination tool. It doesn't explain what constitutes a 'perfil de empresa', how the inputs map to RDL 15/2025 outputs, nor which mandate deadlines/systems are implicated. Given the complexity of the domain and the large sibling set, the description is incomplete for correct tool selection and 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 coverage is 100% – all four parameters (entity_type, province_code, enrolled_in_sii, annual_turnover_eur) already have descriptions in the schema. The tool description adds no extra parameter-level meaning; only 'perfil de empresa' loosely aggregates them. Baseline score 3 is appropriate because the description does not harm or compensate 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?

La description states the tool 'Devuelve los plazos de mandato vigentes y el sistema operativo' for a company profile, so the general action (returns compliance-related data) is identifiable. However, the term 'sistema operativo' is ambiguous in this tax/legal domain, and the description does not distinguish this tool from the many sibling tools (SII, Verifactu, Facturae, Face). It is not a tautology, but lacks precision.

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 explicit guidance tells an agent when to call this tool instead of a sibling (e.g., es__query_sii_status, es__check_b2b_mandate_applicability, es__detect_regional_regime). The reference to RD-ley 15/2025 implicitly suggests it is for mandates under that law, but no when-to-use/when-not-to-use conditions or alternatives are given.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool queries status but does not mention any side effects (though likely read-only), authentication needs, or rate limits. Since the description does not contradict any annotations (none exist), but lacks necessary behavioral context, a score of 2 is appropriate.

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, with two sentences that are front-loaded with the purpose. The status code list is useful and does not add unnecessary length. It could be slightly more structured with a clear 'when to use' line, but overall it is efficient.

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 a single parameter, an output schema (though not detailed), and no annotations. The description is minimal but sufficient for a simple status check. However, without annotations, it lacks details on authentication or potential errors, and the output schema isn't explained. Given the simplicity, this is adequate 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?

The schema already describes the only parameter (invoice_id) as 'Número de registro FACe' with 100% coverage. The description adds no additional meaning beyond reinforcing the domain (FACe). Since coverage is high, a baseline of 3 is appropriate, but the description does not compensate for any lack of 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's purpose: checking the processing status of an invoice in FACe. It specifies a verb and resource ('consulta el estado'), making it easy to understand. Although it doesn't explicitly distinguish it from siblings, the unique verb and resource combination, along with the provided status codes, help 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 for checking invoice status, but does not explicitly state when to use this tool versus alternatives. Among siblings, tools like es__query_verifactu_status or es__submit_to_face exist, but no explicit guidance is given. However, the inclusion of status codes suggests practical usage, but no exclusions or alternatives are mentioned.

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?

No annotations are present, so the description carries the burden of behavioral disclosure. It does explain that XML is normalized into JSON and that EstadoEnvio, CSV, and error details are extracted, but it does not describe behavior on malformed XML, encoding assumptions, or the lack of side effects.

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 definition is compact and front-loaded: the action appears in the first sentence, and the extracted fields in the second. There is no filler, though the 'VERI*FACTU' typo and lack of formatting keep it from being perfect.

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 two-parameter tool with 100% schema coverage and an output schema, the description provides the essential purpose and the key extracted fields, so an agent can invoke it correctly. It lacks explicit usage conditions, but that gap is captured by the usage-guidelines dimension.

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 value by implying that response_type selects between VERI*FACTU and SII, which complements the schema's bare default of 'verifactu'. The xml parameter is mostly restated by 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 specific verb ('Analiza y normaliza'), identifies the exact resource ('respuesta XML de la AEAT (VERI*FACTU o SII)') and the output ('JSON estructurado'). It also names the extracted fields, which clearly distinguishes it from the sibling generation, submission, and status 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 is only implied: an agent would infer to call this tool after receiving an AEAT XML response. It does not explicitly state when to prefer this over siblings, list prerequisites, or mention cases where this tool should not be used.

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?

With no annotations provided, the description carries the full burden. It conveys a read-only intent via 'Consulta' and names the SOAP envelope method, which is useful. However, it does not disclose authentication requirements, potential side effects, rate limits, or whether results are fetched live or cached.

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 purpose. The 'ES-LC-2' replacement note is slightly noisy and not essential for invocation, but it does not significantly harm clarity.

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 output schema exists and all parameters are documented, so most invocation details are covered. Still, the description lacks usage alternatives and behavioral caveats, and the historical REST-replacement note is not enough to fully orient an agent in the broader tool landscape.

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 parameters. The description adds a helpful summary of the main filters (ejercicio, periodo, NIF emisor, número de factura), but this largely restates the schema rather than adding substantial new meaning.

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 consults SII invoice status via specific SOAP operations (ConsultaFactInformadasEmitidas/Recibidas). It is distinct from the sibling Verifactu/Face status tools by explicitly naming the SII context, though it does not explicitly differentiate from those 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?

There is no direct guidance on when to use this tool versus sibling status query tools such as es__query_verifactu_status or es__get_face_invoice_status. The 'ES-LC-2' note about replacing a REST GET is historical context, not actionable selection 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?

With no annotations provided, the description carries the full burden. It discloses that the operation is a query ('Consulta') implying read-only behavior, and it lists the required authentication environment variables (AEAT_ENV, AEAT_CERTIFICATE_PATH, AEAT_CERTIFICATE_PASSWORD). It also states the expected final states it will return. However, it does not explicitly mention error handling or side effects, but the 'consulta' semantics and workflow coverage are sufficient. A minor gap is not stating whether repeated calls are safe or how to handle non-final states, but overall it is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: it starts with the purpose, then gives the precise usage trigger and next steps, and finally lists the required environment variables. Each sentence is purposeful and no filler is present. It is front-loaded with the core action, making it easy for an agent to quickly understand the tool's role.

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 description covers the essential context for correct invocation: it explains when to call (after deferred result), what to wait for (retry_after_seconds), and what to expect (final states). It also states the required environment variables. Since an output schema exists (though not shown), return value details are likely handled there. The only minor omission is guidance on repeated calls or handling unexpected states, but overall it is complete for an agent to use correctly in the described workflow.

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% – each parameter already has a description explaining its meaning (NIF, name, invoice_date, num_serie_factura). The tool description does not add any new information about the parameters; it merely restates the workflow context. Since the schema already documents the parameters well, the description adds no additional value here, meeting the baseline of 3.

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 verb 'Consulta' (query) and the resource: the registration status (EstadoRegistro) of an already-sent VERI*FACTU record. It also references the specific XSD schema, which further pinpoints the operation. This clearly distinguishes it from siblings like es__submit_verifactu_to_aeat (submit) and es__cancel_verifactu_record (cancel), making it unambiguous what the tool does.

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 guidance: use this tool after a 'deferred' result from es__submit_verifactu_to_aeat, wait for retry_after_seconds, and confirm the final state (Correcto / AceptadoConErrores / Anulado) before proceeding. It also mentions required environment variables identical to the sibling submit tool, which helps the agent prepare. This is clear when-to-use guidance with no ambiguity.

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?

No annotations are provided, so the description carries the full burden. It discloses the signing algorithm (SHA-256 + RSA), the default signature policy, and the human-in-the-loop confirmation mechanism. It also clarifies that the certificate password is read from an environment variable and never passed as an argument. This is transparent about the security aspect. It does not mention potential side effects (e.g., whether the input XML is modified or a new file is produced) or error conditions, but for a signing operation the behavior is reasonably well covered.

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 moderately sized with a clear structure: it states the core purpose, then details the signature process, then the confirmation workflow. The human-in-the-loop instruction is prominent and important. It could be slightly more concise (e.g., merging the certificate path explanation), but the length is justified by the complexity of the confirmation flow.

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 that an output schema exists, the description does not need to explain return values. It covers the required parameters, the default behavior, and the confirmation flow. It does not mention validation of the input XML or potential error handling, but those are likely covered by the schema and the tool's implementation. Overall, an agent has enough information to invoke the tool correctly in the intended two-step manner.

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 value by explaining the confirmation_token parameter's role in the two-step flow, the default signature policy for signature_policy_id, and that cert_path refers to a PKCS#12 file. These clarifications go beyond the schema's terse descriptions, providing operational context that helps the agent use the parameters correctly.

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?

Description clearly states it applies XAdES-EPES digital signature to a Facturae XML document, using a PKCS#12 certificate. This is specific and distinguishes it from sibling tools that handle generation, validation, or submission. The verb 'Aplica' and the resource 'documento Facturae XML' are explicit.

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 explicitly outlines the two-step confirmation workflow: call without confirmation_token to receive a summary, then call with the token to apply the signature. This is clear guidance for the intended usage. It does not explicitly contrast with alternatives, but the sibling tools serve different purposes, so usage context is implied. It could be improved by noting when not to use it (e.g., if only validation is needed).

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 discloses key behavioral traits: the batch size limit (10,000 records), the requirement for MTLS certificates, and the two-phase confirmation mechanism. It also implies the tool is a write/submission operation. However, there are no annotations to contradict or complement, and the description does not mention what happens on failure, retries, or the exact structure of the awaiting_confirmation response. Still, the disclosed behaviors go well beyond a minimal description.

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 well-structured: a one-sentence purpose, a one-line prerequisite, and a clear human-in-the-loop instruction. Every sentence earns its place, and the most important operational detail (the two-step confirmation) is highlighted. No fluff 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?

The description covers the essential operational context: prerequisites, batch limit, and the confirmation flow. The output schema exists, so return values are presumably documented there. The main gap is that it doesn't mention error handling or what happens if the token is invalid/expired, but for a submission tool with a clear two-step flow, this is adequate. Slightly more detail on failure modes would make it 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 four parameters. The description adds context for records (SOAP envelopes from es__build_sii_invoice_record) and confirmation_token (from a previous awaiting_confirmation response), which is helpful. However, it does not add much detail about fiscal_year or record_type beyond what the schema already says. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: sending a batch of invoices (max 10,000 records) to the AEAT SII SOAP endpoint. It names the specific resource (SOAP SII endpoint of AEAT) and the verb (submit/send), and the batch limit adds precision. It is distinguishable from siblings like es__submit_verifactu_to_aeat and es__submit_to_face because it explicitly targets the SII SOAP endpoint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: it lists required environment variables (AEAT_ENV, AEAT_CERTIFICATE_PATH, AEAT_CERTIFICATE_PASSWORD) and clearly explains the human-in-the-loop two-step flow: call without confirmation_token to get a summary and token, show it to the user, then call again with confirmation_token to execute. This is strong, actionable guidance that an agent can follow without ambiguity.

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?

No annotations are provided, so the description carries the full burden. It discloses the two-phase human-in-the-loop behavior, the authentication mechanism, and the fact that the first call returns an awaiting_confirmation response. It does not explicitly state that the second call is the actual submission, but that is clearly implied by 'para ejecutar el envío real'. It could add details about side effects or idempotency, but the core behavioral traits are well covered.

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 with the core action, then expands the acronym, then gives authentication context, then the human-in-the-loop flow. Every sentence earns its place. It loses one point because the authentication details are dense and could be slightly more structured, but 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?

The tool has an output schema, so return values are already documented. The description covers the essential context: what FACe is, how authentication works, and the two-step confirmation flow. It does not mention error cases or what happens if the token is invalid, but for a submission tool with an output schema, the provided context is strong. A 4 is warranted because it is nearly complete for an agent to invoke 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 100%, so the schema already documents all five parameters. The description adds context for confirmation_token (explaining it comes from a prior awaiting_confirmation response) and for xml (specifying it must be XAdES-signed), which is useful. However, it does not explain the meaning of administrative_unit, accounting_office, or management_body beyond their schema descriptions, 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 states a specific verb ('Envía'), a specific resource (XML Facturae firmado con XAdES), and a specific destination (FACe via API REST B2B v2). It also expands the acronym FACe, which disambiguates it from sibling tools like es__submit_verifactu_to_aeat and es__submit_sii_batch. The human-in-the-loop confirmation flow further distinguishes it from other submission 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 explicitly explains when to call without confirmation_token (to get a summary and token) and when to call again with confirmation_token (to execute the real send). It also names the authentication requirements (JWS RS256 + x5c, FACE_ENV, AEAT_CERTIFICATE_PATH, AEAT_CERTIFICATE_PASSWORD), which are prerequisites an agent must know before invoking. This is clear when-to-use guidance with no ambiguity.

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?

No annotations are provided, so the description carries the full load, and it does so thoroughly: it discloses the mTLS requirement, FNMT-RCM certificate, required environment variables, the deferred-response behavior, and the two-phase confirmation flow where a call without confirmation_token returns a summary and token rather than executing the real send. This is critical non-schema information.

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 structured as a one-sentence purpose followed by two focused blocks on deferred response and human-in-the-loop flow. It is somewhat longer than minimal, but every sentence conveys behavior that an agent cannot get from the schema or annotations.

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 output schema and the absence of annotations, the description provides all essential surrounding context: environment/auth prerequisites, confirmation workflow, deferred handling, and follow-up tool. Whatever the output schema documents is not discussed, which is acceptable, and no critical gap is evident for an agent to call it 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%, and the description adds value, especially for confirmation_token, explaining that it comes from an 'awaiting_confirmation' response and that a call without it returns a summary instead of executing the real send. It does not add new semantics for nif or xml, but the baseline is 3, and the token detail earns a 4.

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 action: 'Envía un registro VERI*FACTU firmado al endpoint en tiempo real de la AEAT mediante MTLS.' It clearly identifies the operation as submission to AEAT, distinguishing it from query/generate/validate tools. It does not explicitly contrast with sibling submission tools such as es__submit_to_face, though the resource and goal are 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 clear when-to-use guidance: send a signed VERI*FACTU record to AEAT, and if the response has parsed_response.status == 'deferred', wait retry_after_seconds and call es__query_verifactu_status. It also explains the human-in-the-loop call pattern. It lacks explicit when-not-to-use or alternative-tool exclusions, so it falls 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?

With no annotations, the description carries the full burden. It usefully discloses the conditional behavior that complete schema validation only happens if the XSD is available, but it does not state whether the operation is read-only, how errors are returned, or what happens if schema_version differs from 3.2.2.

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 no filler. The core purpose is front-loaded, and the second sentence adds the key conditional behavior without redundancy.

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 validator with an output schema, the description covers purpose and the main behavioral condition clearly. It is slightly incomplete in not explicitly guiding the agent among the many related e-invoicing siblings, but it is adequate for low-complexity 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 100%, so the input schema already documents both parameters. The description adds no additional parameter-level semantics beyond restating the default XSD version, 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 states a specific verb ('Valida'), an exact resource ('XML Facturae'), and a precise standard ('XSD oficial 3.2.2'). This clearly distinguishes the tool from generation, signing, submission, and other Spanish e-invoicing 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 purpose implies use for validating Facturae XML against a schema, but it does not explicitly explain when to choose this over related validation tools or mention exclusions. The only conditional guidance is about XSD availability, which is more behavioral than usage-oriented.

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?

With no annotations provided, the description carries the burden of behavioral disclosure. It explicitly discloses that structural validation is always performed and schema validation only when the XSD is available at a specific path. This conditional behavior is valuable and goes beyond the basic purpose, though it does not mention side effects (likely none) or error semantics.

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-loads the main purpose in the first sentence, then adds a relevant detail about conditional schema validation. No unnecessary words 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?

Given that the tool has an output schema (not shown but noted) and the description explains the validation logic including the XSD availability condition, the description is largely complete. It could mention how schema_version influences XSD selection, but this is a minor gap and likely covered by the parameter description.

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% for both parameters (xml and schema_version), so the schema already documents them. The description adds no additional parameter information, so the baseline of 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 clearly states the tool validates a VERI*FACTU XML record and distinguishes it from siblings like generation, submission, and query tools. The verb 'valida' plus the resource 'registro VERI*FACTU XML' makes the purpose specific and 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 implies the tool is for validating VERI*FACTU XML records, but it does not explicitly state when to use it versus alternatives (e.g., validate_facturae_schema for Facturae). It mentions the conditional schema validation but lacks explicit usage scenarios or exclusions.

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