NexusAI (información pública)

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and side-effect profile is fully covered structurally. The description adds only topical scope (payment, conditions, MCP connection) and says nothing about sourcing or limits, which is acceptable but thin given the bar is lower 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?

A single sentence with no filler, and it front-loads the hiring/payment content before the MCP-connection content. It is slightly list-like and could be split, but nothing 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 zero-parameter, read-only, no-output-schema tool the description covers the needed topics, but it never resolves the ambiguity between the 'contacto' name/title (contact action) and the description (informational guides). An agent calling it cannot predict whether a contact is initiated or content returned.

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, so there is nothing for the description to disambiguate; baseline 4 applies. The schema coverage figure is 100% for an empty object.

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 enumerates topical content (hiring, payment methods, conditions, practical guides, MCP assistant connection) but never states a verb or the kind of operation, leaving it unclear whether the tool retrieves FAQ content or initiates a contact. It differentiates itself from product-oriented siblings by topic, but only implicitly.

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

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

There is no explicit when-to-use statement and no mention of the sibling tools (nexusai_productos, nexusai_detalle_producto, nexusai_recomendar). An agent must infer from the topic list alone that this is the fallback for commercial/onboarding questions.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description correctly does not contradict it. What the description adds is the shape of the returned content (features, audience, pricing, FAQ), useful since no output schema exists, but it says nothing about limits, error behavior for unknown product names, or localization.

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, front-loaded with the scope of returned information, followed by the valid value list. The product enumeration is lengthy but earns its place given the schema has no enum for the producto parameter.

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

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

For a single-parameter read tool with annotations covering safety and no output schema, the description is nearly sufficient: it tells the agent what content comes back and which product values are accepted. Minor gap in not clarifying behavior for an unrecognized product, but 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 coverage is 100% and the schema describes 'producto' as name or id. The description goes beyond the schema by enumerating the valid product catalog (Tienda IA, Gestor IA, Pedidos IA, etc.), which effectively supplies the value set the schema lacks since enums are absent.

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 clear verb+resource: it returns everything about a single NexusAI product (what it does, target user, contents, getting started, price, FAQ). It is specific enough to distinguish from a listing tool like nexusai_productos, though it never names a sibling explicitly.

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

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

Usage is implied rather than stated: an agent can infer this is for drilling into one product rather than listing them, and the enumerated product names signal when the tool applies. There is no explicit when-to-use/when-not, no routing to siblings such as nexusai_productos or nexusai_recomendar.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. With no output schema, the description adds real value by disclosing the payload contents (per-product function, price, link), though it says nothing about formatting or whether the result is static/fixed.

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?

It is front-loaded with what the tool returns and then the usage triggers, with no filler or restatement of the title. The trigger list is long but each item is a concrete retrieval cue rather than padding.

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

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

For a zero-parameter, read-only lookup with no output schema, the description covers both the content of the response (products with function, price, link) and the situations that call for it. The only missing piece is how it relates to nexusai_detalle_producto when a user asks about one specific product.

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, so per the rubric the baseline is 4. There is nothing parameter-related for the description to clarify or omit.

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 resource (NexusAI and its product catalogue) and enumerates the returned fields (what each product does, price, link), so the agent knows exactly what this tool yields. It does not explicitly contrast itself with nexusai_detalle_producto, though the 'lista de sus productos' scope implies the catalogue-vs-single-product split.

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 an unusually concrete when-to-use list of trigger topics (chatbot de WhatsApp, sistema de ventas, agenda de citas, menú QR, contabilidad, etc.), which directly maps user phrasings to this tool. It stops short of naming when-not to use it or routing to the siblings (nexusai_detalle_producto, nexusai_recomendar) for follow-ups.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so safety and side-effect profile are covered. The description adds the return shape—ordered recommendations with reason, price, and how to start—which is useful behavioral context, though it omits volume or pagination 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?

A single front-loaded sentence takes the agent from input to output without filler. The parenthetical examples earn their space by clarifying the input, and 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?

With one required parameter, full schema coverage, and annotations that cover safety and idempotency, the description supplies the missing return-value information since there is no output schema. For a recommendation tool of this complexity, nothing essential is omitted.

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 the single 'negocio' parameter, so the schema already documents the field. The description goes further with concrete examples ('pizzería que recibe pedidos por WhatsApp', 'barbería que quiere recordar citas') that clarify the expected free-text content.

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 verb ('devuelve') and resource ('los productos de NexusAI') and scopes it to a business type and need. It implicitly differentiates from a plain product listing by specifying ordered results with motivo, precio, and cómo empezar, though it does not name a sibling tool.

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

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

Usage is implied by the 'Dado un tipo de negocio y lo que necesita' framing and the two examples, but the description never states when to choose this over nexusai_productos or nexusai_detalle_producto, nor any when-not conditions. No explicit routing guidance is provided.

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