Hogar Montevideo · Agenda de service técnico

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the visit is assigned to the same technician as the original service, the slot must come from the availability tool, and the call returns the new order number, implying each invocation creates a new order (consistent with idempotentHint=false). Error/expiry behavior is not 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?

Three sentences, each carrying distinct information: what gets booked, the required pre-call and confirmation, and the return value. No filler, and the core action is front-loaded.

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

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

For a 7-parameter write tool with no output schema, the description covers the multi-step flow (availability → client confirmation → booking → new order number), which is what an agent needs to sequence calls correctly. It is slightly thin on failure modes and on what the returned order number should be used for next.

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

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

Schema description coverage is 100%, so the schema already documents all seven parameters, including the strict meaning of confirmado_por_cliente. The description adds only the provenance constraint that the day/slot values must come from consultar_disponibilidad_reclamo, which is useful but modest, so the baseline of 3 applies.

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

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

Specific verb + resource ("Agenda la visita de reclamo en garantía") plus distinguishing attributes: mismo técnico del servicio original and the slot coming from consultar_disponibilidad_reclamo. This clearly separates it from the sibling agendar_servicio, which books a normal service rather than a warranty claim.

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 routes the agent through consultar_disponibilidad_reclamo for the slot and mandates confirming day, slot and problem with the client before booking. That is clear when-to-use and prerequisite guidance, though it never states the negative case (e.g. what to do if the warranty token is invalid or the client has not confirmed).

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 the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true). The description adds real value beyond them: it returns an order number, requires explicit client confirmation before booking, discloses the $700 fee if the budget is rejected, and warns that the tool will prompt about recent warranty services. However, it says nothing about what happens if the slot is taken, duplicate-booking risk given idempotentHint=false, or failure modes.

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?

Front-loads purpose and return value, then numbers the three preconditions in execution order, which is easy for an agent to follow. Density is high but every clause carries operational weight; only the parenthetical fee amount is borderline extraneous.

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 16-parameter, 10-required mutation with no output schema, the description covers the critical gaps: prerequisite availability check, required client confirmation, the fee condition, and the warranty-claim branch. It still omits failure handling (slot no longer available, validation errors) and cancellation/rescheduling guidance, which matter for a non-idempotent 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?

Schema description coverage is 100%, so every parameter including enums, patterns and the conditional 'problema obligatorio en reparaciones' is already documented. The description reinforces the franja provenance (tal como lo devolvió consultar_disponibilidad) and the confirmado_por_cliente/ignorar_garantia logic, but adds little meaning the schema does not already carry—baseline 3 applies.

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

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

States a specific verb+resource (reservar la visita de un técnico al domicilio) and even the return value (número de orden), which no other sibling provides. It does not explicitly distinguish itself from agendar_reclamo, which handles the warranty-claim path it references, leaving that boundary implicit.

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?

Gives an explicit pre-call workflow: pick a free slot via consultar_disponibilidad, collect name/celular/dirección/problema, then show a summary and wait for explicit confirmation. It never states when NOT to use it (e.g., warranty claims should go to agendar_reclamo), so the exclusions are only implied.

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/idempotent/non-destructive, so the safety profile is covered; the description adds value beyond that with the result shape ('hasta 5 días hábiles a partir de desde, por defecto desde ahora'), real-time behavior, and the fact that nothing is reserved. It doesn't describe the fields of each returned slot, which matters since there is no output 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?

Three short sentences, each doing distinct work: capability and inputs, return bounds and default, then workflow/constraint. Front-loaded with the action and nothing redundant.

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 availability probe with full schema documentation and no output schema, the description covers inputs, cardinality, default date, and downstream usage. The remaining gap is the shape of an individual returned slot and how the 5-day cap is extended, though 'siguiente_desde' is hinted at 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?

Schema coverage is 100%, so the baseline is 3, but the description adds a genuinely new semantic: the default for 'desde' is 'desde ahora', which the schema only calls 'opcional'. It also frames the three required parameters as conjoint filters on real technician availability rather than static catalog values.

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 ('Consulta en tiempo real los días y franjas horarias en que un técnico ... puede ir al domicilio') plus the three filtering dimensions. It clearly separates itself from agendar_servicio ('usá la elegida en agendar_servicio. No reserva nada'), but never mentions the sibling consultar_disponibilidad_reclamo, which is the closest look-alike and the main source of selection ambiguity.

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?

Explicitly tells the agent what to do with the result ('Mostrale al cliente sólo estas opciones') and what to do next (pass the chosen slot to agendar_servicio), plus a negative constraint ('No reserva nada'). What's missing is guidance on when to prefer this over consultar_disponibilidad_reclamo.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real context: the dependency on a verification token and the explicit statement that nothing is reserved, which prevents an agent from assuming a slot is held.

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?

Three short sentences: what it returns, what it needs, and what it does not do. The most decision-relevant information (the scope of the returned slots) is front-loaded and no sentence is 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 three-parameter read tool with no output schema, the description covers the return content (days and slots), the required inputs, their source tool, and the absence of side effects. The only gap is the lack of any hint about the volume or format of returned slots and how the optional date filter interacts with them.

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

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

Schema coverage is 100%, so all three parameters are already documented, and the description only restates the two required ones plus their provenance. The optional 'desde' filter is never mentioned in the description, so 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 names a concrete resource (free days and time slots) and a specific constraint (only the technician who performed the original service), which distinguishes it from the generic sibling consultar_disponibilidad. It stops short of explicitly naming that sibling, so the differentiation is inferable rather than stated.

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

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

It gives a clear precondition chain: token_garantia and orden_id must come from verificar_codigo_garantia, which tells the agent this tool cannot be the first call in the flow. 'No reserva nada' implicitly routes booking intent to agendar_reclamo, but that alternative is never 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine value beyond that by disclosing the subject matter returned, including the non-obvious detail that the visit cost applies if no repair is made, which an agent needs to answer pricing questions correctly.

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: the first front-loads the provider identity and then lists contents, the second gives the usage instruction. The parenthetical geography is efficient. The content list is dense but each item corresponds to a real question the tool answers, so little 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 no output schema and no parameters, the description carries the full burden of telling the agent what comes back, and it does so by enumerating the returned topics (services, equipment, coverage, slots, conditions, warranty, contact). For a zero-argument informational tool, nothing an agent needs before calling 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, which is the baseline-4 case; there is nothing for the description to disambiguate. The description correctly signals a parameterless lookup by describing it as a consultable catalog rather than hinting at filters that do not 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?

The description names a concrete resource (the Hogar Montevideo service catalog) and enumerates its contents: service types, appliances covered, neighborhoods, time slots, visit-cost conditions, warranty and contact. It also scopes the business geographically (Montevideo and Ciudad de la Costa), which lets an agent distinguish it from the scheduling and warranty-code siblings.

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

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

"Usala para responder dudas o comprobar cobertura antes de agendar" gives a clear trigger (answering questions, checking coverage) and positions it relative to the scheduling siblings by placing it before booking. It stops short of explicit when-not-to-use or naming agendar_servicio by name, so it falls 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.

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

Annotations already declare readOnlyHint=false, openWorldHint=true and non-idempotent, so the fact that this makes an external state change is partly covered. The description adds real context beyond that: a 6-month eligibility window, an internal warranty check that can fail, and an SMS actually being dispatched to the customer. It does not say what happens on a repeat call (does it resend a code, invalidate the old one?) or what the failure mode looks like when the phone has no covered services.

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 dense but purposeful sentences: the first front-loads what happens, the second covers the usage condition and the hand-off to the verification tool. Nothing is redundant, though the second sentence carries three distinct ideas (exclusion, prompting for the code, next call) in one run-on clause.

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, non-idempotent tool with no output schema, the description covers the flow end to end: precondition, action, and next step. The remaining gap is outcome semantics — with no output schema, it never says what a success versus a not-under-warranty response looks like, which matters for an agent that must decide whether to ask the customer for a code.

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% and the celular property already documents the Uruguayan 9-digit 09-prefixed format with an example. The description adds only the implicit notion that this is the contact number receiving the SMS, which is marginal over the schema. Baseline 3 applies when 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?

The description states a specific verb and resource: it checks whether the given cellphone has services under warranty and sends an SMS code, scoped to Hogar Montevideo claims from the last 6 months. It clearly separates itself from verificar_codigo_garantia by naming it as the mandatory follow-up. It does not explain its relationship to agendar_reclamo, the other claim-related sibling, so sibling differentiation is only partial.

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?

"Usala sólo si el cliente quiere reclamar por un trabajo anterior" gives an explicit exclusions clause, and the description names the next tool to call once the code arrives. It still leaves implicit what the agent should do when the condition does not hold (for example, a new rather than prior job), where a sibling such as agendar_reclamo would presumably apply.

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?

Adds real behavior beyond the annotations: the code is single-use, the returned token expires in 60 minutes, and the code arrives by SMS. These are essential operational constraints an agent cannot get from readOnlyHint=false / idempotentHint=false. It stops short of describing failure modes (invalid, expired, already-used code) which would matter for a verification call.

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?

One dense sentence, front-loaded with the action, followed by outputs and downstream dependencies. Every clause carries information, though the sentence is long enough that the token/return-value details could be structured more scannably.

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?

There is no output schema, so the description correctly compensates by naming the returned fields (services with orden_id, token_garantia, 60-minute validity). Combined with the 100%-covered input schema, an agent has what it needs to call this correctly; only error/retry behavior is absent.

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%: both celular (Uruguayan 09-prefixed number with example) and codigo (numeric SMS code, pattern) are fully documented in the schema. The description only mentions the code generically and adds no format or sourcing detail beyond the schema, so the baseline 3 applies.

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

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

States a specific verb and resource ("Verifica el código recibido por SMS") and then spells out exactly what comes back: the in-warranty services for that phone with their orden_id plus a token_garantia. It is clearly separable from solicitar_codigo_garantia (which issues the code) and from the two downstream tools it names.

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?

Explicitly positions the tool as a prerequisite for consultar_disponibilidad_reclamo and agendar_reclamo, so the agent knows where it sits in the flow. It does not explicitly say to call solicitar_codigo_garantia first if no SMS code exists, nor what to do when the code fails, leaving that step to inference.

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