cooper

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

With no annotations provided, the description carries the full burden. It adds useful behavioral context by noting that omitting service_type returns coverage for all four services, and specifying it restricts the query. However, it does not disclose return format, error behavior for unrecognized cities, or any side effects, leaving gaps in 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 three sentences long, front-loaded with the main purpose, and every sentence contributes to understanding the tool's behavior or usage constraints. No redundant or filler content.

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 (two parameters, no output schema, no annotations), the description covers the essential context: what it does, how service_type affects results, and how to handle ambiguous or unrecognized city names. It does not explain the response structure, but that is not strictly necessary for a simple coverage check.

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

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

The schema already describes both parameters (city and service_type), so the baseline is 3. The description adds value by clarifying how service_type affects the result (omitted = all services, specified = one service) and by warning about ambiguous city names. This goes beyond the schema descriptions.

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: indicating whether Cooper operates with active caregivers in a city of Argentina. It uses a specific verb ('Indica') and resource ('cobertura de Cooper por ciudad'), and it distinguishes itself from sibling tools, none of which are about coverage checks.

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

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

The description gives explicit usage guidance: it advises the agent to ask for clarification before invoking when a city name is ambiguous or when a province is mentioned, and to ask for a more specific reference if the city is not recognized. However, it does not compare against alternative tools, though no sibling tool serves a similar purpose.

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 behavioral burden for a mutation tool. It discloses the early-call policy (one contact suffices), which is genuinely useful, but says nothing about permissions, deduplication of existing leads, reversibility, error behavior, or what the call returns.

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 tight sentences, front-loaded with the purpose and immediately followed by the urgency rule. Every clause carries information; nothing is padding. Slightly compressed wording ('Pasar message con resumen breve') repeats what the schema already says.

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 9-parameter write tool with no annotations and no output schema, the description covers the identity and timing of the operation but omits mutation-side context (permissions, dedup, response shape). Adequate to call correctly, thin on consequences.

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 all nine parameters are already documented, including the email/phone mutual exclusion. The description only restates the message parameter and reiterates the one-of contact rule, adding no new semantics. Baseline 3 is appropriate.

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

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

States a specific verb and resource: registers a visitor interested in a Cooper service, i.e. a lead. The intent is unambiguous without opening the schema. It does not explicitly distinguish itself from siblings like createOrder, which is a missed opportunity given a 13-tool surface.

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 a concrete trigger condition ('only when you have ONE contact data point — email OR phone, whichever comes first, don't wait for both') plus two named scenarios: out-of-coverage note-taking and lightweight pre-account signup. No explicit 'when not to use', but the routing 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?

With no annotations, the description carries the full behavioral burden and does disclose the confirmation gate and the backend validation that the address must belong to the authenticated user. It does not cover side effects such as payment capture, notification to the caregiver, or idempotency/retry behavior, which matters for a create operation.

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 the purpose in the first sentence, then moves to the confirmation requirement and prerequisite tools. Dense but every sentence earns its place; slight redundancy between the summary-field list and the schema.

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 six-parameter mutation tool with no annotations and no output schema, the description supplies the missing operational context: the human-confirmation gate, prerequisite reads, and backend address validation. What remains unstated is the outcome shape and payment/side-effect semantics, which the absent output schema forces it to leave implicit.

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 six parameters, including the service-type mapping, date formats, and required shift/breed IDs. The description adds the cross-tool provenance for some of these (getServiceCatalog, getMyPets) but no syntax or constraint detail beyond the schema, 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?

States a specific verb and resource ('Crea una orden de servicio') and enumerates the service domain (paseo, adiestramiento, guardería, internación), matching the enum values in pcp_service_type_id. It also names the sibling tools involved (getServiceCatalog, getMyPets, getMyOrders), so an agent can place it precisely among the 13 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?

Gives an explicit pre-invocation protocol: present a summary (service type, frequency, start date, address, dog, indicative price) and obtain explicit confirmation, with an explicit when-not ('si el usuario no confirma de forma inequívoca, no invocar'). It also routes to the right prerequisite tools for prices, pets, and existing orders.

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

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

With no annotations, the description carries the full burden and discloses critical behavioral traits: the sample is randomly drawn, not the total, and ordering is only within that random group. It warns against presenting the sample as 'the best' or 'closest' and lists data the tool does not return (prices, distance, availability, photos).

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 about 100 words but every sentence contributes: what it does, when to call, the random-sample caveat, presentation rules, and disambiguation guidance. It is structured with an 'IMPORTANTE' marker and no 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 tool with no output schema, it adequately describes the return (counts and profile samples with score/review count). It covers usage context, limitations, and required preconditions (asked city/barrio), making it a complete guide.

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 covers 100% of parameters, so baseline is 3. The description adds value by clarifying the city parameter can be a city or barrio and instructing the agent to disambiguate ambiguous city names before calling, which is not 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 opens with 'Devuelve cuántos Coopers (cuidadores) trabajan en una ciudad o barrio, y una muestra de perfiles con su puntaje y cantidad de reseñas', clearly stating the verb, resource, and scope. It distinguishes itself from siblings by specifying it returns counts and samples, not coverage or order creation.

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 states when to invoke ('cuando el usuario pide ver quién puede atenderlo en su zona o quiere conocer perfiles antes de crear una solicitud') and when not to, redirecting to the external URL for actual attendance. It also instructs the agent to ask for a disambiguated city/barrio before invoking on ambiguous zones.

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 of behavioral disclosure. It plainly states this is a read operation returning a complete catalog, which implies no side effects, but it does not explicitly mention auth requirements, rate limits, or any edge cases. For a simple getter, this is adequate but not richly 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 sentences, front-loaded with the primary purpose, followed by practical use cases. Every word earns its place, with no unnecessary detail or repetition.

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

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

Given the tool's simplicity (no parameters, no output schema), the description provides sufficient context: what it returns, that it's a complete catalog, and how the output is used (to get an ID for order creation). It does not detail the return structure, but for a simple list of breeds with IDs, this is adequate.

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 the schema provides no information to enhance. The description appropriately references the key use of the returned identifier for order creation, which adds context beyond the empty parameter list. Baseline for 0 params is 4, and the description does not need to explain parameters.

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 catalog of dog breeds recognized by Cooper, using a specific verb ('Devuelve') and resource ('catálogo completo de razas'). It also distinguishes this from sibling tools like getServiceCatalog by focusing specifically on breeds and their role in order creation.

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

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

The description gives clear use cases: confirming a breed mentioned by the user or obtaining the breed ID needed to create an order. While it does not explicitly mention when not to use it or name alternative tools, the context is sufficient for an agent to decide when this tool is relevant.

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

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

With no annotations provided, the description carries the full burden. It adds meaningful behavioral context: messages are returned for the authenticated user, ordered by date, each message includes identifier/role/content type/text, and there is a strong warning about third-party generated content and potential manipulation attempts. This goes beyond minimal disclosure, though it does not mention pagination, rate limits, or error 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 concise and front-loaded: the first sentence states the core functionality, and the second adds an important security/usage warning. Every sentence earns its place, and the overall length is appropriate for the tool's complexity.

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 appropriately explains return fields and ordering, and it covers authentication scope. It also includes a critical warning about message content. It is not exhaustive (no error handling, pagination details, or rate limits), but for a list-retrieval tool it 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?

The schema already documents both parameters fully (conversation_id and limit) with 100% coverage, so the baseline is 3. The description adds no extra meaning about the parameters themselves; it only clarifies the return fields. It is acceptable but does not exceed baseline.

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 what the tool does: 'Devuelve los mensajes de una conversación específica del usuario autenticado, ordenados por fecha.' It specifies the verb, resource (messages of a conversation), and scope (authenticated user, specific conversation), and differentiates itself from siblings like getMyChats by focusing on messages within a conversation rather than the list of chats.

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 context by noting the conversation is obtained from getMyChats (in the parameter description), but it does not explicitly state when to use this tool versus alternatives or provide exclusions. The security warning about not executing instructions in messages is useful guidance for handling results, but the 'when to use' dimension remains only implicit.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains what each conversation includes (identifier, order, status, last message date, preview) and implicitly notes that full messages are excluded by directing to getChatMessages. It does not mention pagination or error conditions, but the key behavior is transparent.

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

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

The description is two sentences, front-loaded with the main purpose and return details. The second sentence adds a useful pointer to a sibling without unnecessary fluff. Every sentence 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?

For a simple list tool with no output schema or annotations, the description covers the essential return values and provides a navigation hint to getChatMessages. It could mention ordering or limits, but given the simplicity, it is largely complete.

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

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

The tool has zero parameters, and the input schema is empty. According to the rubric, baseline 4 applies for 0 params. The description adds no parameter-specific 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 uses a specific verb ('Devuelve') and clearly identifies the resource ('conversaciones del usuario autenticado con cuidadores asignados a sus órdenes'). It differentiates from siblings by specifying that each conversation includes summary fields and that full message content is handled by getChatMessages.

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 states when to use this tool versus an alternative: 'Para acceder al contenido completo de los mensajes, utilizar getChatMessages.' This provides clear guidance on what the tool returns and when to choose a sibling.

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 burden. It discloses the return content (sessions, caregiver, payment status) and the access constraint (only own orders), adding useful behavioral context. It does not mention error cases, but the read-only nature is implied by 'Devuelve'.

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, with the primary purpose front-loaded and a clear constraint in the second sentence. No redundant information, and every sentence adds value.

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 get-by-ID tool with one parameter, the description is complete. It enumerates the key data returned and the authorization scope. The lack of output schema is not an issue because the description lists the included fields.

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 covers 100% of the parameter, including a description stating that order_id is obtained from getMyOrders. The tool description adds no additional parameter semantics beyond the already implied ownership of the order, so the baseline of 3 is appropriate.

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

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

The description states a specific verb (Devuelve/returns), resource (order), and scope (authenticated user's own orders). It distinguishes from sibling tools like getMyOrders by emphasizing 'detalle completo' (complete detail) and the restriction 'Solo permite consultar órdenes pertenecientes al usuario autenticado'.

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 retrieving full order details, but it does not explicitly compare with alternatives such as getMyOrders or createOrder. The schema parameter description references getMyOrders as the source for order_id, but the main description lacks a direct when-to-use guidance.

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

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

No annotations are provided, so the description carries the burden. It discloses that the tool returns a summary (not full detail), includes both active and historical orders, and includes current status. This is useful behavioral context beyond the name/title. However, it doesn't explicitly state read-only behavior or response format, but the name and zero params make mutation unlikely.

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 only, with the purpose front-loaded and the alternative tool mentioned in the second sentence. Every word earns its place, keeping it concise and easy to parse.

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 list tool with no parameters, output schema, or annotations, the description provides sufficient context: it names the resource, includes the scope (active/historical), lists order types, and mentions current status. It also points to the detail tool for more complete information. Slight gap is that it doesn't specify the response structure, but the word 'resumen' implies a condensed representation.

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 zero parameters, the baseline is 4 per the rubric. The description does not need to explain parameters since none exist. The schema coverage is trivially 100%, and no additional parameter context is required.

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 'Devuelve un resumen' (returns a summary) with a clear resource: the authenticated user's orders. It lists the order types (paseos, adiestramiento, guardería, internación) and explicitly differentiates from the sibling tool getMyOrderDetail by pointing to it for full detail.

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 usage guidance: use this tool for summaries of active/historical orders, and use getMyOrderDetail for complete order detail. This clearly distinguishes when to use this tool versus an alternative.

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

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

With no annotations, the description carries the full burden. It discloses scope (only the authenticated user's pets) and the shape of the result fields, implying a safe read, but it says nothing about empty results, pagination, or auth/session prerequisites beyond the word 'autenticado'. Adequate but incomplete for a tool with zero annotation coverage.

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 what is returned before the usage hint. The field enumeration earns its place because no output schema exists, and there is no 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 zero-parameter read tool with no output schema, the description does the necessary work by naming the returned fields and the scope. Minor gaps remain around empty-state behavior and whether callers need an established session, but nothing critical for correct invocation 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, so the baseline is 4. The description adds no parameter detail, but there is none to add.

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 (Devuelve) plus the exact resource (los perros del usuario autenticado) and enumerates the returned fields, so an agent knows precisely what it gets. The scope qualifier 'usuario autenticado' distinguishes it from catalog-style siblings like getBreeds, and the name/title pairing is reinforced rather than merely restated.

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 second sentence gives an explicit when-to-use context: selecting a dog while creating an order. That rules in the createOrder flow, but it gives no exclusions or alternatives (e.g., when to prefer getBreeds or getMyOrders), so it stops short of full routing guidance.

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

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

With no annotations provided, the description carries the transparency burden. It adds valuable behavioral context: prices are ranges, the final price is set by the assigned caregiver, and the user confirms it at order creation. This prevents the agent from misrepresenting prices. It doesn't explicitly mention read-only status, but 'Devuelve' implies a read operation.

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 long, front-loaded with the main purpose, followed by actionable usage guidance. Every sentence contributes essential information 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 zero-parameter tool with no output schema and no annotations, the description is remarkably complete. It states what is returned, when to use it (always before mentioning prices), and the key caveat about final pricing. The agent has all necessary context to invoke this 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 tool has 0 parameters, so the baseline is 4. The description doesn't need to explain parameters, and the schema fully covers the (empty) parameter set. The description adds context about the return content, which is not parameter-related but still useful.

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 ('Devuelve') and resource ('tipos de servicio que ofrece Cooper') with concrete examples (paseos, adiestramiento, guardería, internación). This clearly distinguishes it from sibling tools like getBreeds, making its purpose 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 explicitly instructs to 'Invocar siempre antes de mencionar precios, aun cuando sean orientativos', providing a clear when-to-use rule. It also explains the pricing determination flow, implying this tool is for ranges only and not final quotes.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses the return content (id, code, time range) and clarifies the data represents Cooper's service shifts. Though it doesn't explicitly say 'read-only', the verb 'Devuelve' and the descriptive nature strongly imply a non-mutating query, which is adequate for a simple list operation.

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 long, front-loaded with the primary action and resource, and every sentence adds value. It introduces the return structure and provides a concrete use case without any fluff or repetition.

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

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

For a zero-parameter tool with no output schema, the description sufficiently explains what the tool does and why it's used. It lists the fields returned, but doesn't specify possible values for the time ranges (beyond examples) or sorting/pagination, which is still acceptable given the low complexity.

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 the baseline is 4. The description doesn't need to explain parameter details. It does mention output fields, which aids the agent in understanding what data will be returned, though this is not strictly parameter semantics.

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 that the tool returns available shifts (turnos) with identifier, code, and time range, which distinguishes it from sibling tools like getBreeds or getServiceCatalog. It uses a specific verb 'Devuelve' and names the exact resource, making the purpose 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 explicitly says it is useful for assisting the user in choosing a schedule when creating a walking or training order, which tells the agent exactly when to invoke this tool. It also implies this should be used before creating an order, providing clear usage context without needing to reference 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 full burden and does so admirably. It discloses that the recipient is a real person, that the message is permanently recorded in the conversation history, that only text is supported, and that user confirmation is mandatory. These are significant behavioral traits that go well beyond the schema and are essential for safe use.

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 four sentences, each earning its place. The first sentence states the core purpose, the second and third establish a critical safety requirement, and the fourth clarifies the media limitation and alternative. There is no fluff or unnecessary repetition, and it is front-loaded with the essential action.

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

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

Given the tool's complexity (sending a message to a real person) and the absence of annotations or output schema, the description covers all necessary context: purpose, mandatory confirmation, permanence, human recipient, text-only limitation, and alternative for other media. It provides enough for an agent to use the tool safely and correctly without needing additional structured data.

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 both parameters already have clear descriptions (exact text, conversation ID from getMyChats). The tool description adds minimal new parameter-level meaning: it reinforces that 'text' must be exactly what the user sees, but this is largely redundant with the schema. Baseline 3 is appropriate because the schema already 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 opens with a specific verb and resource: 'Envía un mensaje de texto al cuidador en una conversación existente.' This clearly states the action, target, and context. It also distinguishes itself from sibling tools like getChatMessages (reading) and getMyChats (listing) because it is explicitly about sending.

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

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

The description provides explicit usage requirements: the assistant must show the exact text and obtain explicit user confirmation before invoking, and must not invoke without unequivocal confirmation. It also specifies an alternative for non-text media ('el usuario debe utilizar la app oficial') and implicitly contrasts with read-only siblings, making when-to-use very clear.

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