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

Annotations already declare readOnlyHint and openWorldHint, so the description doesn't need to repeat safety. It adds the scope of the search (specific tables) and the ability to query homologation, which is useful behavioral context. It does not disclose output matching behavior or limits, but with annotations covering safety, this is acceptable.

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

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

Two concise sentences with no redundant wording. The core action and options are 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?

The tool is a simple lookup with an output schema, but the description leaves the 'texto' parameter's format or matching semantics undocumented. It also doesn't state whether the search is exact or partial, which an agent needs to know for correct invocation. Overall it's adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the meaning of the tabla enum by listing country, CUIT-per-country, and currency codes, but it provides no guidance on what 'texto' should contain (e.g., exact code, description, partial match). This is a significant gap for a required 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 states a specific action ('Busca') and resource ('tablas de ARCA'), and enumerates the specific code categories (country code, generic CUIT, currency code). It also notes the homologation environment, which helps distinguish it from emission/configuration siblings. However, it doesn't explicitly contrast with siblings, though none do similar lookups.

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 looking up reference codes, and the last sentence explicitly mentions the homologation option. It does not name alternative tools or state exclusions, but the sibling set contains no other search tools, so the context is clear 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?

Annotations already declare idempotentHint=true and destructiveHint=false, indicating a non-destructive, retry-safe mutation. The description adds the specific behavior of canceling a pending confirmation and clarifies that ARCA is not affected, which is valuable context beyond the annotations. No contradictions with the annotations.

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

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

The description is only two sentences, front-loaded with the core action, and avoids unnecessary detail. Every word earns its place, making it highly concise and structured effectively.

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 mutation tool with two parameters and no output schema, the description covers the purpose, scope, and a key side-effect (ARCA untouched). However, it lacks guidance on prerequisites or the exact effect on the draft, and it does not explain the parameters, but given the simplicity, it is mostly complete. A minor gap is the lack of explicit usage alternatives.

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 mention the parameters token or borrador_id at all. It relies entirely on the parameter names, which are only slightly self-explanatory. The description adds no meaning beyond the schema, leaving the agent to infer without any guidance.

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 (cancels pending confirmation) and a resource (the card), and distinguishes itself from ARCA-related operations. It differentiates from siblings like confirmar_emision by specifying it is 'solo para la tarjeta' and does not touch ARCA.

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 ('Solo para la tarjeta') and explicitly notes it does not touch ARCA, which implies when it should be used. However, it does not name specific alternative tools or provide explicit exclusion criteria beyond the card scope, leaving some inference to the agent.

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 destructiveHint=true and readOnlyHint=false, so the agent knows this is a mutating action. The description adds the one-time-use nature of the token and the typed number, which are useful behavioral details. However, it does not disclose what happens to the draft after emission (e.g., deletion, status change) or whether the operation is reversible. With annotations covering the safety profile, the description adds some context but not comprehensive 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 sentence with no filler. It front-loads the usage scope ('Solo para la tarjeta de confirmación') before describing the action, and every word carries meaning. It is appropriately concise and well-structured.

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 destructive tool with three required parameters and no output schema, the description is too sparse. It does not mention the workflow step beyond the vague 'tarjeta de confirmación', lacks prerequisites, and gives no indication of the response or side effects. An agent would struggle to know when to call it and what to expect, making the definition incomplete for safe usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description is the only source of parameter meaning. It clarifies 'token' as a one-time-use token and 'numero' as the typed number, and 'borrador' implicitly maps to 'borrador_id'. However, it does not provide formats, constraints, or how the parameters relate to the action beyond these hints. It partially compensates for the missing schema descriptions but leaves borrador_id ambiguous.

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: 'emite el borrador' (issues the draft) with a one-time token and typed number. It also scopes usage to 'Solo para la tarjeta de confirmación' (only for the confirmation card), which hints at a distinct workflow step. However, it doesn't explicitly contrast with sibling tools like 'emitir_en_produccion' or 'cancelar_emision', so it lacks full differentiation.

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 says 'Solo para la tarjeta de confirmación', which implies it is used in a specific confirmation scenario, but it does not state when to use this tool versus alternatives, nor does it mention prerequisites, sequence steps, or exclusions. No guidance is provided on when NOT to use it or which sibling to choose instead.

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 destructiveHint=true and idempotentHint=true. The description adds the contextual detail 'No afecta nada en ARCA' (does not affect anything in ARCA), which clarifies that this operation has no impact on the production system. It does not contradict annotations and provides extra behavioral context beyond what structured fields convey.

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

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

The description is two short sentences, front-loading the core action in the first sentence and adding a relevant side effect in the second. Every word serves a purpose, with no redundancy or 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 single-parameter destructive operation, the description provides sufficient context: it states the action, the condition for use, and the non-effect on ARCA. It does not describe return values or error handling, but given the simplicity and existing annotations (destructive, idempotent), the description is adequately complete for an agent to call 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?

The input schema has only 'borrador_id' with no description (0% coverage). The description does not explicitly explain the parameter, but the tool's purpose makes it clear that it is the identifier of the draft to delete. The name itself is descriptive, and the context in the description supports inference, though it lacks details such as expected format or 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 the action: 'Borra un borrador que no se va a emitir' (deletes a draft that won't be emitted). It specifies the verb (borra) and resource (borrador), and the phrase 'que no se va a emitir' distinguishes it from emission-related tools. No other sibling performs deletion of drafts, so it is uniquely identifiable.

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 drafts that won't be emitted ('que no se va a emitir'), but it does not explicitly contrast with alternatives or mention when not to use it. There is no reference to sibling tools like 'listar_borradores' or 'cancelar_emision', so the guidance remains implied rather than explicit.

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

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

The description adds significant behavioral context beyond the annotations: irreversibility ('No se puede deshacer'), the only remedy (credit note), the requirement of express approval, and the human confirmation gate. This is exactly the kind of safety-critical behavior an agent needs to know and is consistent with destructiveHint=true.

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

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

The description is front-loaded with the core action and irreversibility, then states the critical preconditions. Every sentence adds essential information; the parenthetical list of confirmation channels is slightly expansive but still useful for an agent deciding whether confirmation has occurred.

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 destructive, high-stakes tool with no output schema, the description covers purpose, environment, irreversibility, preconditions, and parameter matching. It does not describe the success/error response or post-emission workflow, but those are secondary to the safety-critical guidance it provides.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by explaining that numero, receptor, and total must exactly match the values returned by preparar_emision, and that mismatches prevent emission. It does not define borrador_id explicitly, but the draft context and tool name make it inferable. This is strong compensation for a fully undocumented 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 ('EMITE') with a concrete resource ('COMPROBANTE FISCAL REAL') and environment ('ARCA producción'), clearly distinguishing this from preparation, validation, and confirmation tools. It is immediately obvious that this tool performs the real, irreversible emission.

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 when-to-use conditions: only after express user approval of this exact draft, with exact values from preparar_emision, and only after a human confirmation. It also states clear exclusions: if values do not match or confirmation is absent, no emission occurs. This fully routes the agent away from misuse.

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 readOnlyHint=true annotation already declares the safety profile, and the description's 'Muestra' verb is fully consistent with it. The description adds value beyond the annotation by specifying exactly what configuration data is exposed (including certificate expiry), which is useful context for an agent deciding whether to call this before a risky emission action. No contradictions 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 tight sentences with zero waste. The first sentence front-loads the informational content, and the second delivers the usage rule. Every word earns its place; no fluff or repetition of the title.

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?

Complete for a zero-parameter, read-only diagnostic tool whose safety profile is already carried by annotations. The description covers what it shows and when to call it; the absence of an output schema is acceptable for a status/display tool, so nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters and the schema is empty, so the baseline of 4 applies. There is nothing to document, and the description correctly avoids inventing parameter details that don't exist.

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

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

States a specific verb and resource ('Muestra la configuración') and enumerates the concrete contents it reveals: data folder, CUIT, certificates with expiration dates, profile, and issuance-confirmation method. This clearly distinguishes it from siblings like ver_perfil (profile only), ver_csr (certificate only), and probar_conexion (connectivity test), so an agent can disambiguate at a glance.

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?

Provides explicit when-to-use guidance: 'Usala primero si algo falla o si el usuario está configurando' — positioning it as the first diagnostic step on failure or during setup. It does not name specific alternatives or state when not to use it, but the use conditions are concrete and actionable.

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=true and openWorldHint=false. The description adds value by enumerating the finite set of statuses (pending, cancelled, expired, issued), which complements the closed-world annotation. It does not contradict the annotations. However, it doesn't disclose the return format or explain the 'tarjeta' context, leaving the behavioral picture incomplete.

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 compact sentence, which is appropriately sized. However, the sentence is convoluted, front-loading the ambiguous 'Solo para la tarjeta' before the actual status list, which reads as confusing rather than 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?

For a status-check tool with no output schema and an undocumented parameter, the description leaves critical gaps: what 'la tarjeta' refers to, the meaning and format of borrador_id, and the return shape. An agent cannot reliably invoke this tool correctly without additional context, especially given the cryptic domain terminology.

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 0%, so the description carries the full burden of explaining borrador_id, yet it never mentions the parameter at all. The phrase 'un token para esta apertura' is oblique and does not clearly map to borrador_id. An agent has no way to understand what value to pass or how it relates to the confirmation status.

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 the tool reports the confirmation status by enumerating the possible outcomes (pending with summary and token, cancelled, expired, or already issued). This does distinguish it from the sibling 'estado_configuracion' (configuration status). However, 'Solo para la tarjeta' (only for the card) is ambiguous — it never clarifies what 'the card' refers to in this domain, and the run-on phrasing obscures the core purpose.

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 offers no explicit guidance on when to use this tool versus siblings like confirmar_emision, cancelar_emision, or preparar_emision. The only hint is the opening 'Solo para la tarjeta,' which is a scope restriction but is unexplained and gives no actionable condition for selection, and no alternatives are named.

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 supply idempotent/non-destructive behavior. The description adds a meaningful external boundary—'No toca ARCA'—which is not derivable from annotations and tells the agent this operation has no tax-authority side effects. It doesn't describe the output or overwrite behavior, but the annotation safety profile lowers the 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 tight sentences, front-loaded with the action and resource, with 'No toca ARCA' as a high-value one-line caveat. No filler or repetition of schema titles.

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 idempotent/non-destructive annotations, the core purpose and side-effect boundary are clear. But with no output schema, the description doesn't say what the tool returns, and the unexplained 'archivo' parameter means an agent still has to guess a key part of the call.

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 never explains 'archivo' or 'entorno'. 'Archivo' is especially ambiguous (file path? comprobante ID?), and while the enum gives controlled values for 'entorno', its effect on the operation is unspecified. The phrase 'de un comprobante guardado' gives only a loose hint about the required 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 opens with the specific action 'Regenera' and the object 'PDF de un comprobante guardado', and names the exact design ('Comprobantes en línea'). The closing 'No toca ARCA' separates it from ARCA-focused sibling tools, so there is no ambiguity about what this tool is for.

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

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

It gives clear context: regenerate a PDF for an already-saved comprobante, without touching ARCA, so the agent can infer it is for PDF re-generation rather than emission, cancellation, or ARCA setup. It does not name a sibling alternative or list explicit when-not conditions, which keeps it a point below the strongest definitions.

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 idempotentHint=true and destructiveHint=false, so the description correctly adds behavioral context: it verifies the certificate is not a CSR, checks the environment, and ensures it corresponds to the key before saving. This is valuable beyond annotations, though it doesn't describe failure behavior, which is acceptable given the safe profile.

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 with a colon separating the main action and verification from environment-specific instructions. It is front-loaded with the purpose and contains no filler, making it efficient and perfectly sized.

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 everything an agent needs to call the tool correctly: the verification prerequisites, the required `entorno`, and which optional parameter to use in each case. With no output schema and safe annotations, no critical information 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 0%, so the description fully compensates: it explains `certificado` for homologación (text from WSASS, from -----BEGIN CERTIFICATE-----) and `ruta` for producción (path to .crt). It also implies `entorno` values via the Homologación/Producción mapping. No parameter meaning is left ambiguous.

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 the exact purpose: 'Guarda el certificado que dio ARCA' (saves the certificate given by ARCA), and distinguishes it from CSR handling ('no el CSR') and clarifies it is for the correct environment and key. This clearly separates it from siblings like ver_csr (view CSR) and guardar_perfil (save profile), so an agent can identify when to use 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?

It provides explicit usage instructions: for homologación use the `certificado` parameter, for producción use `ruta`, and only after verifying it is a certificate (not a CSR) and matches the key. This gives clear when-to-use and when-not-to-use guidance, and implies alternatives (e.g., not for CSR).

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 indicate this is non-read-only, idempotent, and non-destructive. The description adds meaningful behavior beyond annotations by specifying partial-update semantics: passed fields are updated and 'el resto queda como está'. This clarifies the merge behavior without contradicting 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 core behavior is front-loaded in the first clause, and the field enumeration is dense but organized through nested braces. It is long because it documents a complex object, though line breaks or a list format would improve readability.

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 opaque schema, nested objects, and lack of output schema, the description is remarkably complete: every field, nested subfield, and allowed value is specified. An agent has enough information to construct a valid perfil object without opening other references.

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 provides almost no information: perfil is just an object with additionalProperties true and 0% schema coverage. The description fully compensates by listing all accepted keys, nested object structures, allowed enum values, and even null semantics for punto_venta_prod_comunes.

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: 'Actualiza perfil.json con los campos que se pasen'. It clearly distinguishes this write/update operation from sibling read tools like ver_perfil, and it enumerates the exact fields involved.

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 the tool for persisting profile settings. However, it does not explicitly state when to use it versus alternatives, nor does it provide any exclusions or prerequisites beyond the partial-update behavior.

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

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

Annotations already mark the tool read-only and non-open-world, and the description adds behavior beyond that: omitting 'seccion' returns the complete guide while named sections return that part. Nothing about the description contradicts the annotations.

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

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

The description is compact and front-loaded: the purpose appears first, and the parameter behavior follows in one short sentence. A minor clarity improvement would be to phrase the default behavior as a complete sentence, but it remains 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?

For a one-optional-parameter reference tool with an output schema and read-only annotations, the description covers the necessary selection behavior and section inventory. It does not detail each section's contents, but that is not required for the agent to 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 0%, but the description compensates by listing all section values and defining the null case ('Sin sección, la guía completa'). It adds useful labels such as 'paso1 (clave y CSR)' and 'homologacion (WSASS)' that the enum alone would not convey.

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 the resource ('alta en ARCA') and the deliverable (step-by-step guide plus error table), which is clear even though it lacks a strong verb. It does not explicitly differentiate from the operational sibling tools, but the reference nature is evident from 'Guía'.

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 explains the main usage decision: 'Sin sección, la guía completa' and enumerates the selectable sections. It does not discuss when to prefer this over sibling tools, but for a documentation tool the context is clear and no exclusion 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?

Beyond the idempotentHint=true annotation, it discloses that an existing key is never overwritten, that the private key is never returned, and that the returned CSRs are public. This is valuable non-obvious behavior an agent needs to set expectations.

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 main behavior is front-loaded and the parameter bullets are compact and useful. The final bullet loses a line break and the text is denser than needed, but no sentence is wasted.

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

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

For a side-effectful setup tool with no output schema, it adequately describes the generated artifacts, their return, and idempotent retry behavior. Missing output details (e.g., what else the response includes or what happens if a key already exists) prevent a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description compensates by giving real-world meaning and formats for nombre, alias, condicion_iva, ingresos_brutos, and inicio_actividades. It falls short on cuit format and omits domicilio_comercial, and it slightly conflates nombre with razon_social despite both existing in the schema.

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

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

The description names a specific action ('Paso 1 del alta') and concrete effects: crea carpeta de datos, guarda CUIT/datos del emisor, genera clave privada y CSR. It differentiates from sibling tools by being the initialization step and by referencing the CSR that later steps like ver_csr/guardar_certificado handle.

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 frames when to call it ('Paso 1 del alta') and states that it can be re-invoked with the same CUIT to complete emitter data. It doesn't list exclusions or name alternative tools, but the first-step context is unambiguous.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds that the tool returns drafts from homologation with specific statuses (validado, emitiendo, emitido), which is useful context. However, it doesn't mention ordering, pagination, or other behavioral details, though the output schema likely covers the return format.

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, concise sentence that conveys the core purpose and scope without fluff. It is front-loaded with the primary action and context, making it easy for an agent to scan and understand quickly.

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 simplicity (no parameters, output schema present), the description is nearly complete. It specifies the resource (drafts validated in homologation) and the returned status values. It doesn't mention any limitations or edge cases, but this is acceptable for a straightforward read-only list operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema coverage is trivially 100%. Per the baseline for no parameters, the description need not add parameter details, and it doesn't. The description adds no parameter-related information because none is needed.

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 lists drafts ('borradores') that have been validated in homologation and shows their status. It is specific about the resource and action, and the term 'borradores' distinguishes it from sibling tools like listar_comprobantes, though it doesn't explicitly name 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?

No guidance is provided on when to use this tool versus other list tools or under what circumstances. The description only states what it does, not when it should be chosen or which scenarios it is not suitable for.

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 openWorldHint=false, so the read-only nature is covered. The description adds valuable context by stating the data source (carpeta de datos) and ordering (newest to oldest), which are not present in annotations or 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 two sentences: the first states the core purpose and ordering, the second explains the filter parameter. It is front-loaded and compact, 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?

Although an output schema exists, the description does not explain the meaning or defaults of `limite` and `entorno`, which are essential for an agent to call the tool correctly. It only covers `buscar`, leaving significant context missing for a list endpoint with multiple options.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains that `buscar` filters by text and lists searchable fields, but it leaves `limite` (limit) and `entorno` (environment) entirely undocumented. For a tool with 3 parameters and zero schema descriptions, this is only partial coverage.

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

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

The description clearly identifies the resource (comprobantes guardados en la carpeta de datos) and the order (del más nuevo al más viejo), which distinguishes it from siblings like ultimo_comprobante (single record) and listar_borradores (drafts). The verb 'listar' in the title reinforces the action.

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 specific use case for the `buscar` parameter (filter by client name, file, date), but does not explicitly state when to choose this tool over alternatives like ver_comprobante or ultimo_comprobante. The intended usage is implied rather than 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=true and openWorldHint=true, so the description's 'Solo lee de ARCA' reinforces this and adds specificity about what is read. It also discloses that it returns specific fields and that it is a non-destructive preparation step, providing context beyond the annotations without 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 concise sentences, front-loaded with the purpose and return values, with no redundant information. Every sentence contributes to understanding what the tool does and when to use it.

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

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

For a simple tool with one parameter and no output schema, the description covers the essential context: it is for production, works on a draft, returns preview data, and is read-only. It lacks mention of error conditions (e.g., invalid draft) or the exact format of returned data, but these are minor given the clarity of the purpose and the data fields listed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the single parameter borrador_id. It indirectly does so by saying 'de un borrador SIN emitir', indicating it is the ID of a draft. However, it does not provide additional details like format, required attributes, or how to obtain the ID, relying on the schema's title 'Borrador Id'. It adds some context but not sufficient to fully compensate for the lack of schema description.

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: preparing an emission from a draft without emitting, and specifies exactly what it returns (voucher number, recipient, total, exchange rate) for user approval. It distinguishes itself from siblings like emitir_en_produccion (which emits) and confirmar_emision (which confirms) by explicitly noting it does not emit.

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 conveys when to use this tool: before asking the user for approval, to show real data from a draft. While it doesn't name alternatives explicitly, the workflow context with siblings (emitir_en_produccion, confirmar_emision) implies it is the preliminary step. It could be improved by explicitly stating 'use this instead of emitir_en_produccion when you need to preview before emitting', but the purpose is clear.

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

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

The description aligns with the readOnlyHint and adds detail about what is tested (service status, login, points of sale). It also specifies the invoice types per service, which is extra context beyond the annotations. However, it doesn't mention other potential behaviors like rate limits or error handling, but for a simple read-only test that's acceptable.

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

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

The description is one sentence, front-loaded with the read-only nature, and efficiently packs the service details. No fluff or redundant information. Every phrase 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?

Given the low complexity (2 parameters, no output schema), the description covers the core purpose and service details. It doesn't describe the return format, but for a test tool that's likely just a status result. The environment parameter is a gap, but overall it's complete enough 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?

The schema provides enums for both parameters, but description coverage is 0%. The description explains the services (wsfe, wsfex) and their invoice types, which adds meaning for 'servicio'. However, it doesn't explain the 'entorno' parameter (homo vs prod) at all, so the semantics are incomplete. The agent knows the enum values but not their implications (e.g., homologation vs production environment).

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's a read-only test of service status, login, and points of sale, and specifies the invoice types for each service (wsfe: A, B, C; wsfex: Factura E). This distinguishes it from sibling tools that handle emission, confirmation, cancellation, etc. The purpose is 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 it's a connectivity test but doesn't explicitly state when to use it versus alternatives. There is no exclusion or condition for when to use this tool instead of others, nor any mention of prerequisites. The read-only nature is clear, but no scenario guidance is 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?

The annotations already declare readOnlyHint and openWorldHint, and the description adds useful behavior beyond them: the number is obtained from ARCA, and an omitted point of sale defaults to the production profile's point of sale or the first active one. This default-selection behavior is not present in the annotations or 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 one compact sentence with no filler or repetition. The main object is front-loaded, and the default-selection caveat is placed in a parenthetical where it does not distract. It is concise but slightly terse for a tool with four parameters.

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 read-only query, the description plus schema and annotations is mostly adequate: safety is covered, allowed inputs are enums, and the point-of-sale default is explained. However, there is no output schema and no guidance on the nota_credito parameter or the intended workflow, leaving some gaps for an agent selecting and invoking the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description should compensate, but it only alludes to 'tipo de comprobante' and 'punto de venta'. It does not explain the meaning of 'entorno' beyond indirectly mentioning production, and it never explains the nota_credito boolean. The schema provides allowed values, but parameter semantics remain under-specified.

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: the last ARCA-authorized voucher number for a given comprobante type and point of sale. This distinguishes it from listar_comprobantes and ver_comprobante, which return lists or individual documents. It loses one point because it lacks an explicit verb like 'obtener' or 'consultar' and the title/description are very close.

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 given about when to use this tool instead of listar_comprobantes, ver_comprobante, or before calling emitir_en_produccion. There are no exclusions, workflow cues, or alternative tool mentions. The intended usage is left entirely to inference.

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

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

Annotations already indicate readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds that it emits in homologation without fiscal value, conditionally creates a draft, and mentions a workaround for test dates. This provides behavioral context beyond annotations, such as the conditional draft creation and the non-idempotent nature implied by the action. No contradiction found.

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 long, each carrying value: the action and outcome, the usage condition, and parameter hints. It is concise and front-loaded, with no redundant information. It could be slightly more structured, but 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?

This is a mutation with conditional behavior, no output schema, and a nested parameter. The description explains the action and the conditional outcome (creates draft if approved) but does not specify what the tool returns, what happens if not approved, or how to interpret the result. It also lacks details on error handling and prerequisites beyond user confirmation. For a tool with this complexity, the description is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate. It states that `factura` follows the format described in server instructions (a pointer rather than a full explanation) and explains that `punto_venta_homo` is for avoiding previous test date errors. This gives some meaning but does not detail the structure of the nested factura object, leaving gaps for an agent.

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 an invoice by emitting it in homologation (test environment, no fiscal value) and conditionally creates a draft for production if ARCA approves without observations. It uses a specific verb (valida) and resource (factura) and distinguishes from siblings like emitir_en_produccion by specifying the homologation context.

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 to call only after the user has confirmed the data, providing a clear when-to-use condition. It also explains the purpose of punto_venta_homo for avoiding date errors from previous tests. However, it does not explicitly mention alternatives or when not to use it, though the sibling context implies this.

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

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

Beyond the readOnlyHint annotation, the description discloses the return behavior: a complete JSON representation of a saved comprobante, with the 'factura' field carrying the original data. This is useful context for an agent deciding whether the output is sufficient. It does not detail error cases or response shape beyond JSON, but for a simple read tool the disclosure is adequate.

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

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

A single compact sentence that front-loads the core output ('JSON completo de un comprobante guardado') and then clarifies the 'factura' field's purpose. There is no filler or redundant restating of the title.

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

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

For a read-only tool with no output schema, the description does explain the main return value and its purpose. However, it omits clarification of the required 'archivo' parameter and the surrounding retrieval context. The definition is minimally viable but leaves an agent guessing about how to identify the target comprobante.

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 0% description coveragehola, and the description does not explain 'archivo' or 'entorno' at all. An agent must infer that 'archivo' is the identifier/path of the saved comprobante and that 'entorno' switches between homologation and production. The description adds no parameter-level meaning, leaving a significant ambiguity gap for a required argument.

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 complete JSON of a saved comprobantelands, including the original data in the 'factura' field des. It is distinct from siblings like listar_comprobantes or generar_pdf because it focuses on retrieving the full stored record for reuse or credit-note construction. However, it does not explicitly name or contrast against sibling alternatives, so it stops short of a 5.

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

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

The description gives explicit use cases: reusing the original data or building a credit note from it. This tells an agent when the tool is appropriate. It does not mention when not to use it or point to alternatives, so it lacks the exclusionary guidance needed for a 5.

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

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

Annotations already declare readOnlyHint=true, and the description adds that the CSR 'Es público' (is public), reinforcing that no sensitive data is involved. It also clues the agent into the expected payload shape (texto, ruta del archivo y alias) without contradicting the read-only annotation.

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 each clause carries distinct information: output components, environment-specific usage, and publicness. The colon-and-semicolon structure is slightly awkward but no content is wasted.

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

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

For a simple one-enum, read-only tool with no output schema, the description supplies the necessary scope, environment variants, and a hint at the return fields. It does not explicitly state 'returns', but the title and parenthetical make the behavior clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate for the undocumented 'entorno' parameter. It does so by mapping the two values to 'homologación' and 'producción', so an agent can infer that 'homo' and 'prod' select the environment.

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 title 'Ver el pedido de certificado (CSR)' names the action (view) and the resource (certificate request/CSR), and the description narrows the scope to 'un entorno' with homologación/producción variants. It is clear that this is a retrieval tool for CSR data, though the description itself is a noun phrase and does not state the verb.

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 downstream context: the homologación CSR is pasted into WSASS and the producción CSR is uploaded as a file in Digital Certificates Administration. It does not explicitly say when to choose this tool over siblings or when not to use it, so the usage guidance is implied rather than stated.

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, so the read-only nature is known. The description adds the specific content of the return (fields), which is useful for an agent. It does not disclose any additional behavioral aspects like authentication requirements or error conditions, but given the simple read operation and existing annotations, this is adequate.

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

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

A single, compact sentence that front-loads the action and resource. It lists all the returned fields without redundancy, making it highly efficient and easy to parse quickly.

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 is the sole source of return information. It covers all the relevant fields (including date rules) so an agent knows exactly what to expect. For a parameterless, read-only tool, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, and the schema coverage is 100% (trivially). The description correctly implies no arguments are needed and does not introduce confusion. The baseline for 0-parameter tools is 4, and the description maintains that.

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 the verb 'Devuelve' (returns) and the specific resource 'perfil.json', and enumerates the exact fields returned (nombre, puntos de venta, condición IVA, cliente, formato, reglas de fechas). This clearly distinguishes it from the sibling 'guardar_perfil', which is the write counterpart.

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 is immediately clear from the name and description—it retrieves the profile. However, it does not explicitly state when not to use it or contrast with the alternative 'guardar_perfil'. The context is unambiguous enough that no further guidance is necessary, but explicit routing would be ideal.

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