Directorio Systema

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

There are no annotations, so the description carries the full behavioral disclosure burden. It adds a useful boundary by noting that tickets must be purchased on the event's own web page, but it does not describe output shape, ordering, pagination, or any explicit read-only side-effect 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 description is short, front-loaded, and structured by clear Spanish and English sections. Every clause adds relevant information; there is no fluff, tautology, or unnecessary detail.

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 low-complexity tool with three optional filters and no output schema, the description covers what the tool returns exists, where it comes from, how to filter, and that purchase happens externally. Minor gaps remain such as explicit ordering or result-field list, but they are not critical for successful use.

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 provides 100% coverage for all three parameters with bilingual descriptions. The text restates the filter dimensions (text, city, days) but adds no meaningful parameter semantics beyond what the JSON schema already provides.

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 explicitly names the resource ('eventos públicos próximos' from directory businesses) and describes searchable event types (concerts, fairs, shows). It is clearly distinct from sibling tools like buscar_negocios or ver_promociones.

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 clearly states the intended use: find upcoming public events from the directory and optionally filter by text, city, or days. It does not explicitly mention alternative tools or when not to use it, but the context is clear enough for a simple search tool.

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 mentions the fallback behavior when no location or city is provided, which is a useful behavioral trait. However, it does not disclose other behaviors like pagination, sorting, or error handling, and there are no annotations to supplement.

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 no redundant words, and clearly structured in both English and Spanish. It efficiently conveys the necessary information without 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 absence of an output schema, the description adequately covers the tool's core functionality and a key behavioral nuance. It does not address limitations like result quantity or sorting, but these are not critical for basic understanding.

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?

While the schema includes descriptions for each parameter, the tool description adds context about optionality—specifically that omitting location and city yields a country/global listing. This additional semantic enriches the parameter understanding beyond the raw 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 clearly states the tool searches businesses in a public directory for Miami–Central America, with specific filters. It distinctly differentiates from sibling tools like event search or reservation tools.

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

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

The description implies use for business searches but does not explicitly state when to prefer this over alternatives. It lacks direct guidance on when not to use it, such as when searching events or making reservations.

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 burden, but it does disclose the return behavior (returns each business with matched items and price or 'cotizar'). However, it does not mention potential side effects (e.g., search-only, no writes) or any data limits. The absence of annotations and lack of behavioral details keep this at a 3.

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 (bilingual) and front-loads the core purpose immediately. It includes examples and the sibling complement without excess. However, the bilingual repetition doubles length without adding new content, slightly reducing efficiency, but it remains concise overall.

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 moderate complexity (3 parameters, one nested object, no output schema), the description adequately explains the search semantics and return structure. It does not cover possible edge cases like empty results or pagination, but for a search tool with no output schema, this is reasonably 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 baseline is 3. The description adds context for the main 'consulta' parameter through examples, but does not provide additional semantics for 'ciudad' or 'ubicacion' beyond their schema descriptions. The value added is minimal, hence a score 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 a specific verb ('search') and resource ('businesses by what they offer'), with concrete examples ('zumba classes', 'men's haircut') and explicitly distinguishes from sibling tool buscar_negocios by contrasting the search dimension (offering vs name/category). This fully differentiates it from the closest sibling.

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 states when to use this tool (when searching by offering) and explicitly complements buscar_negocios, implying an alternative for name/category searches. It does not explicitly say when not to use it, but the clear complement relationship provides sufficient context for selection decisions.

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 it returns hours per staff with staffId, which is useful. However, it does not mention any side effects (likely none, as it is a read operation), nor does it clarify edge cases like no availability or invalid dates. The description is functional but not deeply 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 two concise sentences, providing the core purpose and key output detail (staffId) without fluff. It is bilingual but efficient, with no wasted words. Front-loads the main action immediately.

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 simplicity of the tool (3 params, no output schema, no annotations), the description covers the essential aspects: purpose, optional filter, and return format. It lacks details on error cases or no-slot scenarios, but for a basic availability query, it is reasonably complete. The links to related tools (buscar_negocios, ver_negocio, reservar_cita) enhance 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 description coverage is 100%, so parameters are documented. The description adds valuable cross-tool context, e.g., slug is 'from buscar_negocios' and service name is 'as shown by ver_negocio', which helps the agent know where to get these values. It also clarifies the servicio is optional. This goes beyond the schema and earns a higher score.

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: 'Free appointment slots for a date' and 'Returns hours per staff member with staffId'. It uses a specific verb (consultar/check availability) and resource (appointment slots), and distinguishes from siblings like reservar_cita by explicitly noting the output is 'ready for reservar_cita', indicating it is a pre-booking step.

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 use case: it is for checking availability before booking, as indicated by 'ready for reservar_cita'. It also mentions the optional service filter. However, it does not explicitly state when not to use it or mention alternatives, though the sibling context makes the flow clear. This is adequate but not exhaustive.

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 full behavioral burden. It discloses that the review is real, public, saved under the customer's name, requires consent, has a rate limit, and uses the phone for deduplication. This is solid but could be more explicit about side effects (e.g., it cannot be retracted) and possible errors (e.g., failure if duplicate or business not found). Still, it gives significant behavioral context beyond raw functionality.

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—two sentences in both Spanish and English—front-loaded with the core action. It packs purpose, consent, rate limit, and dedup into a compact format without redundancy. Each sentence contributes meaning.

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 mutation tool with no annotations, the description covers essential aspects: what it does, the public nature, consent requirement, and rate limit. It omits potential error scenarios (e.g., duplicate review, invalid phone) and does not describe return values, but given the lack of output schema and the tool's relative simplicity, the description is reasonably complete for an agent to invoke 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% with each parameter already having a clear description (e.g., 'telefono' states 'NOT published; dedup only'). The description adds marginal value by reiterating the dedup purpose and rate limit, but doesn't introduce new parameter semantics beyond what the schema already 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 action: 'Publishes a real PUBLIC review (1-5 stars + text) under the customer's name on the business listing.' This is a specific verb (publish) with a resource (review on business profile) and scope (real, public, under customer's name). It distinguishes itself from siblings like reserving, ordering, or searching by making the intent unmistakable.

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 clear context for usage: it requires explicit customer consent and enforces a rate limit (max 1 per phone per 24 h per business). However, it doesn't explicitly say when to use this tool versus alternatives (e.g., 'Use this when the customer wants to leave a review'), though it's obvious from the name and purpose. The constraints are valuable usage guidelines but not comparative alternatives.

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 disclosing behavior. It transparently states the order is real, payment is cash upon pickup/delivery, and that the server resolves actual products and never invents prices. It also mentions delivery conditions. However, it omits potential side effects like cancellation or order confirmation 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 bilingual but still brief and to the point. It packs essential information into two short paragraphs without redundancy. Every sentence adds value, covering the action, payment method, key input requirements, and delivery constraints.

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 there is no output schema, the description does not explain what the tool returns (e.g., confirmation, order ID) or how errors are handled (e.g., item unavailable). While it sets expectations for the input and payment, it lacks information about the response or failure modes, leaving some incompleteness for a full user interaction.

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 descriptions for most parameters (86% coverage), and the tool description adds practical guidance on what values to pass (e.g., item names from ver_negocio, cash payment, delivery address requirement). The 'cantidad' parameter lacks a description in the schema, but the description doesn't clarify it either, so a minor gap exists.

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: placing a real food/product order paid in cash, with explicit pickup or delivery options. It distinguishes itself from sibling tools like reservations or appointments by focusing on food ordering.

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 implicitly indicates when to use this tool (for food orders) and provides specific instructions such as sending item names exactly as shown in ver_negocio and the requirement for an address for delivery. However, it does not explicitly state when not to use it or contrast with alternatives.

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 mentions that confirmation arrives via WhatsApp/SMS, which is a behavioral outcome, but it doesn't disclose that this is a write operation (creating a booking) or mention potential side effects like conflict handling. This is a moderate gap given no 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 concise and well-structured, with bilingual text that duplicates but doesn't add fluff. It efficiently communicates the core action, prerequisite, and result without unnecessary detail.

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 absence of an output schema and annotations, the description covers the prerequisite and the confirmation outcome. However, it doesn't address error scenarios, idempotency, or the exact effect on the system (e.g., whether it's a final booking). This is adequate for a simple booking tool but lacks some context for full 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 description coverage is 88% (7/8 parameters described). Most parameters have meaningful descriptions, including sources (from consultar_disponibilidad) and formats (HH:MM, YYYY-MM-DD). The 'notas' parameter lacks a description, which is a slight gap, but overall semantics are clear.

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 books a real appointment as a guest, distinguishing it from other sibling booking tools like reservar_clase or reservar_habitacion. It also emphasizes 'REAL' to indicate an actual booking 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 explicitly instructs to use consultar_disponibilidad first to pick time and staffId, providing a clear prerequisite. It implies the tool is for guest booking, though it doesn't explicitly mention when not to use it, but the context is sufficient.

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 full behavioral burden. It says 'Books the customer into a REAL class' and mentions validation, but it does not disclose side effects (e.g., permanent reservation, whether cancellations are possible), required permissions, or what happens on success/failure. For a mutation tool with zero annotation support, this is a significant gap.

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 bilingual but concise, clearly stating the action, target, validation logic, and prerequisite reference. Every sentence contributes meaning, and it is front-loaded with the primary purpose.

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 completes the schema context: it clarifies the class source (ver_negocio), validation rules, and the guest approach. Since there is no output schema, the description doesn't need to explain return values, but it could benefit from mentioning error-handling specifics or confirmation. Overall, it is fairly complete for a booking 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?

Schema coverage is 100%, with each parameter described. The tool description reinforces the source of the class name (ver_negocio) and that it's for guest bookings, but it doesn't add extra semantics beyond what the schema provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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?

Clearly states it books a customer into a REAL gym class as a guest, with name and phone, on a date. Distinguishes 'real class' from other tools and references ver_negocio for class lookup, making the intent 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 using ver_negocio first ('Classes are listed by ver_negocio') and clarifies this handles guest bookings, differentiating it from other reservation tools. However, it does not explicitly state prerequisites or when NOT to use this tool versus alternatives like reservar_habitacion.

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 does add useful context: the booking is real, payment occurs at the hotel, and the response includes nights and total. However, it does not disclose potential side effects like duplicate bookings, cancellations, or whether confirmation/availability checking is required.

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, front-loaded, and bilingual without unnecessary wording. Both sentences contribute to understanding the action, inputs, output, and payment behavior.

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 there is no output schema, the description usefully explains what is returned and that payment happens at the hotel. The schema covers the rest of the parameter detail. It is not perfect because it omits potential repeat-call implications and cancellation/confirmation behavior, but it is reasonably complete for a booking tool.

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

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

The input schema already describes all parameters at 100% coverage, so the baseline is 3. The description adds little beyond repeating room name, dates, and guest count; it mentions that the room name comes from ver_negocio, but the schema already states that. No meaningful extra parameter semantics are provided.

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 action ('Reserva/Books a REAL hotel room as a guest') and clearly identifies the resource, inputs, and return behavior. It also distinguishes this from sibling tools like reservar_cita and pedir_comida by explicitly saying hotel room booking.

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 indicates this is for hotel room bookings and mentions that the room name comes from ver_negocio, giving the agent the correct source context. It does not explicitly state when not to use it or name alternatives, but the hotel-room wording and sibling names make the use case fairly 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?

With no annotations provided, the description carries the behavioral disclosure burden. It explicitly warns that this is a REAL request, that the business gets notified, and that they may call the customer's phone — important side effects beyond a mere form submission. It does not detail response behavior or failure modes, but the real-world impact is disclosed.

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 bilingual sentence, front-loaded with the core action and key qualifiers. It conveys purpose, target audience, and real-world effect without padding or 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?

Given the 7-parameter schema with full descriptions and no output schema, the description covers the essential invocation context: what the tool does, who receives the request, and the real-world consequence. It is not overly verbose, though it could mention what happens after submission or whether confirmation is 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?

Schema description coverage is 100%, so the schema already explains each parameter clearly, including the phone purpose and where the slug comes from. The tool description adds no parameter-level meaning beyond emphasizing the real notification and phone callback, which is already echoed 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 clearly states the action, resource, and scope: sending a real estimate request to a services business, with examples of eligible contractor types. This distinguishes it from sibling tools like reservar_cita and solicitar_visita_inmobiliaria by focusing specifically on service estimates.

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 clear context for when to use the tool: when a customer needs an estimate from a services/contractor business. It does not explicitly name alternatives or exclusions, but the domain and action are specific enough to avoid obvious misuse alongside the sibling tools.

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 emphasizes that the inquiry is REAL (not a test/simulation) and explains that the realtor receives the lead and contacts the customer. However, it doesn't disclose potential side effects like customer data being shared with a third party, rate limits, or whether multiple requests can be sent. The 'REAL' emphasis is helpful, but more behavioral detail (e.g., does it create a lead in a CRM, is it a one-way communication?) would improve transparency.

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: two bilingual sentences (ES and EN) that front-load the core purpose and workflow. Every phrase adds value, including the emphasis on REAL and the outcome (realtor contacts customer). No filler or repetition.

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

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

For a lead-generation tool with 12 parameters and no output schema, the description provides a good overview of what the tool does and the high-level process. It lacks details on what happens after submission (e.g., no confirmation response, no guarantee of visit) and doesn't discuss idempotency or retries. However, the tool is relatively straightforward: submit a lead form. Given schema coverage and no output schema, the description is reasonably complete, though it could mention that the lead is not a booking confirmation.

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 75%, so most parameters have descriptions. The tool description adds context by explaining the overall purpose of the fields (property of interest, budget, move-in date, pets) and clarifies that the lead goes to the realtor. However, it doesn't explain all parameters; for instance, 'mensaje' and 'habitaciones' are not described in the tool description, leaving some gaps. Overall, it adds enough semantic context to aid selection and invocation.

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 sends a REAL inquiry to a real-estate business with specific fields (property, budget, move-in date, pets), and explains the workflow (realtor receives lead and contacts customer). This is a specific verb+resource+outcome and distinguishes it from sibling tools like reservar_cita or solicitar_estimado.

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 indicates when to use it: when a customer wants to express interest in a property and have the realtor contact them to arrange a visit. It doesn't explicitly name alternatives or exclusions, but the context of real-estate inquiry vs appointment booking is implied. It could be more explicit about not using it for booking a specific time slot (use reservar_cita) but the intent 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?

No annotations are provided, so the description carries the full burden. It does not explicitly state that this is a read-only operation, nor does it mention potential side effects, permissions, or error behavior. The description lists content but lacks behavioral clarity.

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 extremely concise, providing one sentence in each language without extraneous content. It efficiently communicates the scope of the profile.

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 enumerates the main components of the business profile (hours, rating, catalog, promotions, events, links), which is fairly comprehensive for a view operation. It does not mention pagination or response format, but that is not critical for a single-business profile retrieval.

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 provides a description for the slug parameter ('from buscar_negocios'), and the tool description does not add additional meaning beyond that. Baseline of 3 is appropriate due to full schema 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 states the action ('View business profile') and the resource (business by slug). It distinguishes itself from sibling tools like buscar_negocios (search) and ver_promociones (view promotions) by focusing on a full profile given a specific slug.

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 when a slug is available and a comprehensive profile is needed. It does not explicitly state when not to use it, but the context of sibling tools provides enough guidance for an 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?

With no annotations, the description carries the behavioral burden and clearly discloses that omitting location/city returns the country/global scope, and that only 'active' promotions are returned (implying a read-only operation). It does not delve into response format or pagination, but for a simple query this is sufficient.

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

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

The description is two compact sentences, provided in both Spanish and English, with the key action and object front-loaded. It contains no filler and effectively communicates the tool's functionality and default behavior.

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 query with two optional parameters and no output schema, the description adequately covers input modes and the default scope. It could mention result ordering or limits, but those are minor gaps given the tool's simplicity and the parameter documentation in the schema.

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 has 100% description coverage: 'Filter by city' and 'The USER's location (not the agent's)'. The tool description only restates the parameters ('by location {lat,lng} or city') without adding new semantic details, so the baseline score 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 it returns 'Active promotions from directory businesses' and explains the two filtering modes (location/city) with a country/global fallback. This specific verb+resource combination distinguishes it from sibling tools like ver_negocio (view business) and buscar_negocios (search businesses), which are about businesses rather than promotions.

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 promotions, optionally filtered by location or city, and it explains the no-filter fallback. However, it does not name alternative tools or provide explicit when-not-to-use guidance, which keeps it just 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.