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. The description only states the action 'approve' but does not disclose side effects, permission requirements, reversibility, or what happens to the payroll period after approval. This is a significant transparency gap for an action that likely mutates state.

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

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

The description is a single, concise, front-loaded sentence that communicates the core action and a key constraint ('previously calculated') without any wasted words.

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

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

For a simple one-parameter action, the description provides the essential context that this is an approval step following calculation. However, it does not explain what happens after approval (e.g., whether it enables payment), and there is no output schema or annotations to fill that gap. The tool is adequate but not comprehensive.

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 has 100% coverage with a single parameter 'id' described as 'ID del periodo de nómina'. The description adds no additional meaning beyond the schema, so the baseline score 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 explicitly uses a specific verb 'Aprueba' (approve) and resource 'periodo de nómina' (payroll period), and adds the qualifier 'previamente calculado' (previously calculated). This clearly distinguishes it from sibling tools like calculate_payroll, pay_payroll, and create_payroll_period.

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 phrase 'previamente calculado' clearly indicates the tool should be used after calculation, providing contextual guidance for the workflow. However, it does not explicitly mention alternatives or exclusions, so it does not reach the highest bar of explicit when/when-not 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 were provided, so the description carries the full burden. It discloses support for split shifts, breaks, and day off, but it does not explain update behavior (e.g., whether it replaces the entire shift), the effect of isOff on time fields, or any required permissions. The description reads as a feature list rather than a behavioral disclosure.

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, front-loaded sentence that conveys the primary action and key features in under 20 words. Every clause adds 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?

Despite having 11 parameters and no output schema or annotations, the description provides a clear high-level overview. However, it omits operational details such as how isOff interacts with time fields, the role of absenceType, and what happens when assigning to a day with an existing shift, leaving gaps for a complex 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 schema covers all 11 parameters, meeting the >80% coverage baseline of 3. The description adds value by grouping startTime2/endTime2 as 'jornada partida' and breakStart/breakEnd as breaks, and by highlighting isOff as a day-off flag, clarifying relationships between parameters beyond individual 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 action with specific verb 'Asigna o actualiza' (assigns or updates) and identifies the resource as employee shifts ('turno de un empleado en un día'). It also highlights key capabilities (split shifts, breaks, day off) that distinguish it from schedule-viewing tools like gerent365_get_schedule.

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 creating or updating employee shifts but does not explicitly state when to use it versus alternatives such as gerent365_get_schedule or gerent365_copy_week. There is no mention of exclusions or when not to use it, so guidance is 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions what is calculated and the state restriction, but it fails to disclose side effects (e.g., whether it mutates data or changes the status), what happens if called on an invalid state, or whether it is idempotent. The action 'calcula' implies a possible mutation, but this is not explicitly stated.

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, with two sentences that each add essential information: the action and scope, and the applicability condition. Every word earns its place, and it is front-loaded with the core 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?

Despite having only one parameter and 100% schema coverage, the description lacks essential contextual details. There is no output schema, so the description should explain what the call returns or how it affects the period state. The tool likely mutates data (e.g., transitioning from DRAFT to CALCULATED), but this is not disclosed, making the description incomplete for a tool that performs a calculation.

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 coverage is 100% with a single 'id' parameter described as 'ID del periodo de nómina.' The tool description adds no extra semantic information about the parameter, so the baseline score of 3 is appropriate. The state restriction is usage guidance rather than 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 uses a specific verb 'Calcula' (calculates) and identifies the resource 'nómina de un periodo' (payroll of a period), with explicit details on what is computed (hours worked, tips, Puerto Rico taxes). It also includes a relevant state constraint (DRAFT or CALCULATED), clearly distinguishing it from sibling tools like approve_payroll or pay_payroll.

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 clearly states when to use the tool via the phrase 'Solo aplica a periodos en estado DRAFT o CALCULATED' (only applies to periods in DRAFT or CALCULATED state), giving an explicit exclusion of other states. However, it does not name any alternative tools for states outside these statuses, so it falls 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?

No hay anotaciones y la descripción no revela detalles de comportamiento importantes, como si se sobrescriben turnos existentes en la semana destino, cómo se manejan conflictos, o si la operación es segura o reversible. La descripción es demasiado escueta para una operación que modifica datos.

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?

La descripción es una oración simple y directa, sin palabras innecesarias. La acción principal está al frente, lo que facilita la lectura rápida.

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?

Para una operación de copia que puede afectar datos, la descripción es incompleta. No indica qué ocurre con los turnos de la semana destino, si se reemplazan o fusionan, ni el formato de respuesta. Sin anotaciones ni esquema de salida, la descripción debería ofrecer más contexto.

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?

El esquema ya cubre el 100% de los parámetros con descripciones claras. La descripción del tool repite esa información en prosa sin añadir detalles sobre formato, restricciones o significado semántico adicional.

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?

La descripción indica claramente la acción de copiar todos los turnos de una semana origen a una semana destino. Es específica y se distingue de herramientas hermanas como assign_shift, que maneja turnos individuales.

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

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

No se proporciona orientación sobre cuándo usar esta herramienta frente a alternativas como assign_shift o publish_schedule. La descripción solo implica el caso de uso de copia masiva, sin exclusiones ni alternativas.

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 present, and the description does not disclose any behavioral traits such as authentication needs, idempotency, duplicate handling, or side effects. The phrase 'Crea un nuevo cliente' is purely a statement of action with zero transparency about what happens when invoked.

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

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

The description is a single sentence with no unnecessary words, making it concise. However, it is under-specified for a tool with 10 parameters; the extreme brevity sacrifices essential information, so it is not appropriately sized 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?

With 10 parameters, no output schema, and no annotations, the description is severely incomplete. It provides no information about return values, side effects, parameter details, or usage context, making it inadequate for an agent to correctly select and invoke the tool.

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

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

The input schema has 10 parameters with only 40% description coverage, and the tool description mentions none of them. It fails to compensate for the missing schema descriptions, leaving fields like tags, email, allergies, and isVip unexplained, which is critical for correct 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 'Crea un nuevo cliente.' clearly states the action (create) and resource (customer), with 'nuevo' distinguishing it from update operations. However, it does not explicitly reference sibling tools like update_customer or list_customers, so differentiation relies on the tool name rather than the description.

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 no guidance on when to use this tool versus alternatives like update_customer or create_employee. It lacks any context about prerequisites, intended scenarios, or exclusions, offering only a bare definition with no usage direction.

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, leaving the description to bear the full burden of behavioral disclosure. The description only says 'creates a new employee' and does not mention potential side effects, required permissions, validation rules, or what happens on duplicate emails. This is minimal transparency 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?

The description is a single, concise sentence with no wasted words, earning points for brevity. However, it is so minimal that it lacks essential context, making it slightly less effective than a perfectly structured description that balances conciseness with informative 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?

Despite having 9 parameters and no annotations or output schema, the description provides no information about expected return values, edge cases, or prerequisites. This is insufficient for a creation tool with complex inputs and no other source of behavioral context.

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

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

The input schema has 100% coverage with descriptions for all 9 parameters, so the baseline is 3. The tool description adds no parameter-level meaning beyond what the schema already provides, so no additional credit is warranted.

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 'Crea un nuevo empleado en el negocio' (Creates a new employee in the business), which clearly identifies the action (create) and resource (employee). It implicitly distinguishes from sibling tools like update_employee and delete_employee, but does not explicitly mention alternatives or additional context.

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

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

There is no guidance on when to use this tool versus other employee-related tools, nor any mention of prerequisites, exclusions, or alternatives. The description simply states the action without contextual direction.

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 must disclose behavioral context. It only states the basic create action and mentions some fields; it does not mention side effects, permissions, required fields, or what happens on success/failure. This is a significant gap for a mutation tool with no annotation support.

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

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

The description is a single, concise sentence that conveys the core purpose without unnecessary words. It is front-loaded with the verb and resource, making it easy to scan.

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 five parameters, one required, no annotations, and no output schema, the description is too sparse. It does not mention that 'name' is required, explain the 'description' parameter, or indicate what response to expect. For a create operation, more context is needed for successful invocation and error handling.

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 description lists three of the five parameters (hourly rate, color, department), which helps summarize the tool's intent. However, it does not clarify the two parameters missing descriptions in the schema ('department' and 'description'), and the schema already describes name, color, and hourlyRate. With 60% schema coverage, the description adds marginal value but does not fully compensate for undocumented 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 action ('Crea un nuevo puesto de trabajo' = creates a new job position) and identifies the primary resource. The verb 'crea' distinctly separates it from sibling tools like update, delete, and list, making the tool's 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 implies usage: you would use this tool when you need to create a job position. However, it provides no explicit guidance on when not to use it or alternatives (e.g., updating an existing position). The context is straightforward enough for a CRUD create operation, but no direct comparison to siblings is given.

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, and the description carries the full burden of behavioral disclosure. It only states that a new payroll period is created, without mentioning side effects, prerequisites, authorization needs, or return values. This is insufficient for a mutating 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 a single, front-loaded sentence that efficiently conveys the core function. No unnecessary words 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?

With no output schema and no annotations, the description omits crucial information such as return values, validation rules, or operational constraints. The brief text leaves significant gaps for a tool with five parameters and no supporting structured metadata.

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 description. The description adds marginal value by summarizing the date range and tip options, but does not enrich understanding of parameter semantics beyond 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 ('creates a new payroll period') and identifies key attributes (date range, tip inclusion options). It does not explicitly differentiate from sibling payroll tools, but the unique resource and verb make its purpose clear.

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

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

No guidance is provided on when to use this tool versus alternatives like calculate_payroll or list_payroll. The usage context is only implied by the presence of creation verbs and parameters, so the description lacks explicit decision support.

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 for behavioral transparency. It only states the action 'creates' without disclosing side effects, required prior conditions (e.g., category must exist), validation rules, or the response format. For a mutation tool, 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 a single clear sentence that is front-loaded with the action 'Crea'. It is concise with no filler, but it is perhaps too sparse given the tool's complexity, which slightly lowers the score from a perfect 5.

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

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

The tool has 11 parameters, no output schema, and no annotations. The description provides minimal context, omitting return value, error behavior, or any operational nuance. It is insufficient for an agent to fully understand the tool's behavior in context.

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 64%, leaving several parameters undocumented. The description's mention of 'precio, categoría e impuestos' adds little beyond the schema's existing parameter descriptions, and it does not help clarify undocumented parameters like stock, minStock, or trackStock. It fails to compensate for the coverage gap.

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 'Crea un nuevo producto' (Create a new product), specifying the verb and resource with precision. It mentions price, category, and taxes, but does not explicitly distinguish itself from sibling tools like list_products or create_product_category, so it loses a point for lack of explicit differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. It implies use for creating products but lacks any contextual guidance, earning a low score.

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 present, so the description must disclose behavior. It indicates a write operation ('crea') but provides no information about side effects, permissions, return values, or error handling. This is a mutation tool and the lack of behavioral context 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 a single short sentence, front-loaded with the verb and resource. It contains zero waste and is immediately scannable.

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 create operation with 4 scalar params, the description is minimal but adequate. It does not mention expected outcomes or prerequisites beyond the schema, but the schema already specifies required fields. Given no annotations or output schema, a bit more context (e.g., return value) would be helpful, but it is not critically incomplete.

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

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

Schema description coverage is 75% (3 of 4 params documented). The description adds no parameter-specific details beyond the schema, but the existing schema descriptions are clear. The undocumented 'description' parameter is not compensated for, but the high schema coverage makes this acceptable.

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 ('Crea') and resource ('categoría de productos'), clearly distinguishing it from sibling tools like list_product_categories (listing) and create_product (product). It is unambiguous and action-oriented.

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

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

No usage guidance is provided. The description does not state when to use this tool, prerequisites, or alternatives, leaving the agent to infer from the tool name and siblings. There is no explicit 'when to use' or 'when not to use.'

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 hay anotaciones y la descripción no revela efectos secundarios, validaciones, requisitos de permisos, comportamiento en errores ni formato de respuesta. Para una herramienta de mutación esto es una laguna crítica.

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?

La descripción es una oración breve y directa, sin relleno ni redundancia. Es fácil de procesar y cumple con el requisito de brevedad, aunque a costa de omitir detalles importantes.

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?

Para una herramienta de creación con 8 parámetros y sin schema de salida, la descripción es insuficiente para entender el resultado esperado, validaciones, efectos secundarios o contexto de uso. No se menciona qué devuelve ni qué condiciones se aplican.

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?

La cobertura del schema es del 88%, por lo que los parámetros ya están documentados con descripciones claras. La descripción del tool no añade información adicional sobre los parámetros, pero el baseline de 3 es adecuado dado el alto nivel de detalle del 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?

La descripción 'Crea una nueva reservación' especifica la acción (crear) y el recurso (reservación), distinguiéndola claramente de herramientas como update_reservation o list_reservations. Aunque es breve, el verbo y el objeto son precisos y no hay ambigüedad sobre la intención.

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

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

No se ofrece ninguna orientación sobre cuándo usar esta herramienta frente a alternativas como update_reservation o list_reservations. La descripción no menciona condiciones de uso, limitaciones ni criterios de selección.

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 of behavioral disclosure. It only says 'creates a new table' without revealing side effects, permission requirements, uniqueness constraints on the 'number' field, or any validation behavior. This is minimal for a write 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 a single, concise sentence that front-loads the action and included fields. Every word earns its place, with no fluff 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?

For a simple create-table tool with no output schema and modest parameter complexity, the description is adequate but leaves gaps: it doesn't explain when to use it, any side effects, or required permissions. Given the lack of annotations and minimal guidance, it is minimally viable but not contextually rich.

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 provides descriptions for 4 of 5 parameters (80% coverage), so the baseline is 3. The description merely repeats the field names (number, capacity, location) without adding significant meaning or clarifying edge cases, but it does align with the schema and adds a hint about the 'location' parameter despite it not being 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 clearly states the action ('Crea una nueva mesa') and the key attributes (número, capacidad, ubicación), distinguishing it from sibling tools like gerent365_list_tables (which lists) and gerent365_create_reservation (which creates reservations). The verb and resource are specific and unambiguous.

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

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

There is no guidance on when to use this tool versus alternatives, nor any mention of prerequisites or contexts to avoid. The description simply states what it does, leaving the agent to infer usage from the tool name and sibling context.

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 only states that a request is created, without disclosing side effects, permissions, approval processes, or success/failure behavior. This is insufficient for a mutation tool.

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, front-loaded sentence with zero wasted words. It is concise and directly states the core purpose, earning top marks for efficiency.

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 create operation with 5 parameters and no annotations or output schema, the description is too sparse. It does not mention what the tool returns, how it behaves on errors, or any usage context, leaving significant gaps for an agent to select and invoke it safely.

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 parameters and their formats are already well-documented in the schema. The description adds no additional parameter context, matching the baseline expectation for high 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 'Crea una solicitud de ausencia para un empleado' clearly states the specific action (create) and resource (time off request for an employee), effectively distinguishing it from sibling tools like list_time_off and update_time_off.

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

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

There is no guidance on when to use this tool versus alternatives. The description simply states the function without mentioning any prerequisites, exclusions, or specific scenarios, leaving the agent to infer that it is for creating new time off requests.

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 present, so the description carries the full burden. It only says 'crea' (creates) but does not disclose side effects, idempotency, permissions, or what happens if a pool for the same date already exists. This is a significant transparency gap for a mutation tool.

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

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

The description is a single, concise sentence that is front-loaded with the verb and resource. Every word earns its place, 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?

The tool is simple with 4 parameters all documented in the schema. The description, while minimal, covers the core purpose. However, the lack of annotations and any behavioral context (e.g., whether the operation is idempotent or requires specific permissions) leaves gaps, making it minimally viable but not 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 the context of 'montos en efectivo y tarjeta' which maps to cashAmount and cardAmount, but does not provide additional syntax or constraints beyond what the schema already describes.

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 verb 'crea' (creates) and the resource 'pool de propinas' (tip pool) for a specific date, with cash and card amounts. This distinguishes it from sibling tools like list_tips and distribute_tips.

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

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

No guidance is provided on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or relationships to sibling tools such as distribute_tips or list_tips.

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 of behavioral disclosure. It only states that it retrieves statistics and gives examples of content, but does not mention whether it is read-only, what the return format is, or any other behavioral traits. It is not misleading, but it lacks depth.

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

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

The description is a single, concise sentence that front-loads the main action (obtiene) and resource (estadísticas del dashboard). Every word serves a purpose, and the parenthetical examples are helpful without being verbose.

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 is adequate but has gaps. It does not specify what exactly the statistics include beyond examples, nor does it differentiate from the potentially overlapping sibling gerent365_report_dashboard. More context on return structure or usage scope would improve 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?

The tool has zero parameters, so the baseline is 4. The description adds useful context by listing examples of what the statistics include (sales, employees, activity), which gives the agent an idea of the data scope, even though there are no parameters to clarify.

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 retrieves business dashboard statistics (sales, employees, activity, etc.), providing a specific verb and resource. However, it does not distinguish this from the sibling tool gerent365_report_dashboard, which may serve a similar reporting purpose.

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

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

No guidance is given on when to use this tool versus alternatives. The existence of sibling tools like gerent365_report_dashboard suggests potential overlap, but the description does not clarify when one should be preferred over the other.

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 full responsibility for behavioral disclosure. It only states the action without revealing whether deletion is permanent, cascades to related data, requires special permissions, or what happens if the ID is invalid. This is a significant gap for a destructive 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 a single, front-loaded sentence that is both concise and informative for such a simple tool. Every word adds value, with no fluff 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 tool's simplicity (one parameter, no output schema), the description covers the core purpose adequately. However, it omits outcome details and consequences of deletion, which are important contextual elements for an agent to set expectations. The lack of annotations or output schema increases the need for such information.

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% for the single 'id' parameter, so the description adds little beyond what's already in the schema. Mentioning 'por su ID' reinforces the parameter's role but provides no extra format, constraints, or examples.

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 ('Elimina') and resource ('empleado') with a clear scope ('por su ID'), making the tool's purpose unambiguous. It naturally distinguishes from sibling tools like create, update, or list employee operations.

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

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

No explicit when-to-use or alternative guidance is provided. The usage is implied by the tool's name and description—delete an employee by ID—but there is no mention of prerequisites, such as whether the employee must not have related records, or when to avoid using it.

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?

There are no annotations, so the burden falls on the description. It does not disclose that deletion is permanent, whether associated records are affected, or any permission requirements. The only behavioral detail is the action itself.

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, front-loaded sentence that directly states the action and scope. It is concise and free of unnecessary words, scoring highly for structure.

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 a one-parameter delete, the description is functionally adequate but lacks any mention of side effects or return value. For a destructive operation with no annotations, it would benefit from cautionary context.

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 the 'id' parameter with its description, so the description's mention of 'ID' adds no new information. Since schema coverage is 100%, a baseline score of 3 is appropriate, though no additional semantic detail is 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 verb 'Elimina' (delete) and identifies the resource 'puesto de trabajo' (job position) with the method 'por su ID' (by its ID), making it distinctly the deletion tool among siblings like create/update/list job positions.

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

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

No usage context is provided; it simply states the deletion action and the ID parameter. There is no guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions.

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 for behavioral disclosure. It only states the action without revealing consequences such as whether the distribution is irreversible, affects payroll, or updates the tip pool status. This is insufficient for a mutation tool.

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

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

The description is a single sentence, front-loaded with the purpose, and contains no filler. Every word adds value, efficiently covering both usage modes.

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 annotations or output schema, the description should disclose behavioral details. It covers purpose and parameter usage but omits side effects, return values, or conditions. Given the moderate complexity and good schema coverage, it is minimally adequate but has clear gaps.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explicitly linking parameters into two usage patterns ('method' + employeeIds, or manualDistributions) and gives an example method ('por horas trabajadas'), clarifying their relationship beyond 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 tool distributes a tip pool among employees, using a specific verb ('Distribuye') and resource ('pool de propinas'). It distinguishes from sibling tools like create_tip_pool and list_tips by indicating the action of distribution.

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 on how to use the tool by explaining two modes: using 'method' with employeeIds, or manual distributions. It does not explicitly mention when not to use it or alternatives, but the context is clear enough for a simple management 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?

No annotations are provided, so the description carries the full burden. It only states the tool gets attendance records and can filter; it does not disclose read-only nature, required permissions, output format, pagination, or other behavioral details. The verb implies retrieval but side effects are not explicitly ruled out.

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

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

The description is a single concise sentence that immediately conveys the purpose and filtering capability. Every word contributes meaning with no 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?

The tool is straightforward, but without annotations or an output schema, the description does not specify return values or edge cases. It covers the basic filtering options adequately, but leaves room for more detail on what the response looks like.

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 description restates that filtering by employee and date range is possible, but adds no new detail beyond the schema, such as parameter interactions or default values. Baseline 3 for high schema coverage 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 retrieves attendance records (fichajes) using the verb 'Obtiene' (gets), and notes filtering by employee and date range. This distinguishes it from related siblings like get_last_punch (specific punch) and get_schedule (schedules).

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 attendance records but doesn't explicitly state when to use this tool versus alternatives like get_last_punch. No exclusions or alternative recommendations are provided, so guidance is implied rather than explicit.

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

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

No annotations are provided, so the description must carry the behavioral transparency burden. The verb 'obtiene' implies a read-only operation, but the description does not explicitly state safety side effects, authentication requirements, or potential errors. It is a simple getter, so the implied behavior is clear, but there is no additional detail beyond the action itself.

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, front-loaded sentence in Spanish. It is concise, includes illustrative examples, and contains no fluff. Every word contributes to conveying the tool's 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?

Given the tool is a simple getter with no parameters and no output schema, the description provides a good list of returned fields (name, email, phone, address, timezone, settings) but leaves room for ambiguity with 'etc.'. It does not describe the return structure or whether all business settings are included, but it is reasonably complete for the tool's simplicity.

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

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

The input schema has zero parameters, so the description has no parameter semantics to explain. Per the rubric, with 0 params the baseline is 4. The description adds context about the returned fields, which is helpful, though not directly about 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 verb 'obtiene' (gets) and the resource 'información del negocio del usuario autenticado' (business information of the authenticated user). It lists specific fields (name, email, phone, address, timezone, settings) which makes the purpose unambiguous and distinguishes it from siblings like gerent365_get_employee (employee data) and gerent365_get_profile (user profile).

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: to retrieve business information for the authenticated user. However, it provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. The context suggests it is the canonical getter for business data, but the description does not articulate this.

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

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

With no annotations, the description carries the full burden. The verb 'Obtiene' implies a read-only operation, which is a positive signal, but the description does not disclose error behavior (e.g., what happens if the ID doesn't exist) or any permission requirements. It adds minimal behavioral context beyond the verb itself.

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

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

The description is a single, concise sentence with no fluff. It is front-loaded with the action and resource, making it immediately scannable.

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 and no output schema, the description is adequately complete: it states what it does and how. It could mention the return shape (e.g., the full employee object), but given the simplicity and the pattern of sibling tools, the gap is minor.

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% (the 'id' parameter has a description), so the baseline is 3. The description's 'por su ID' simply restates the parameter's purpose without adding new semantics like format, examples, or constraints, but it does confirm the parameter's role.

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 ('Obtiene' = gets) and resource ('los datos de un empleado') with a clear filter ('por su ID'). It clearly distinguishes from sibling tools like list_employees, which retrieves all employees, and create/update/delete mutations.

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 'por su ID' phrase clearly indicates this tool should be used when you have a specific employee ID and need that employee's data. It provides clear context, though it doesn't explicitly exclude other tools or list alternatives like list_employees for broader queries.

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 responsibility for behavioral disclosure. It only states what the tool does, without revealing edge-case behavior, return format, side effects, or error handling. It does not even explicitly confirm this is a read-only 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 a single, concise sentence with no filler or repetition. It is appropriately sized for the tool's simplicity and gets straight to the point.

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

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

The tool has no output schema and no annotations, so the description must explain return values and context. It does not describe what a 'punch' entails, the structure of the returned data, or behavior when no punch exists. This leaves significant gaps despite the simple operation.

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

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

The input schema fully documents the single parameter 'profileId' with a clear description ('ID del empleado'). Since schema coverage is 100%, the baseline of 3 applies; the description adds no extra parameter details but also doesn't need to.

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: retrieving the last punch (fichaje) for an employee. It uses a specific verb ('Obtiene') and resource ('último fichaje'), distinguishing it from related tools like gerent365_get_attendance or gerent365_kiosko_punch.

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 no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or exclusions, and there is no reference to sibling tools or scenarios where this tool is preferred.

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 says 'gets notifications' but doesn't specify whether this is a read-only operation, whether it marks notifications as read, what authentication is required, or what the response structure looks like. This is a minimal description that leaves important behavioral aspects undisclosed.

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, clear sentence with no unnecessary words. It immediately conveys the core action and resource, making it highly concise and well-structured. There is zero redundancy or filler.

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

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

For a simple tool with one optional parameter and no output schema, the description is minimal but lacks key contextual details. It doesn't explain what a 'notification' is, how the results are ordered, whether pagination is involved, or what the response format includes. The low parameter count and lack of annotations mean the description should provide more context, but it falls short.

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 fully documents the single parameter 'unreadOnly' with the description 'Devolver solo las no leídas' (Return only unread ones). The description adds no additional meaning beyond this, and since schema coverage is 100%, the baseline of 3 is appropriate. The description neither clarifies nor conflicts with the 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 the verb 'Obtiene' and the resource 'notificaciones del usuario/negocio', making it evident what the tool does. However, the scope 'usuario/negocio' is slightly ambiguous—does it return notifications for the current user, the business, or both? There are no sibling notification tools, so differentiation isn't needed, but the ambiguity prevents a perfect score.

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 no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, typical use cases, or exclusions. Since no sibling notification tools exist, the need for explicit alternative references is reduced, but the description still lacks any contextual advice.

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 transparency burden. It explains the operation and mentions the endpoint, giving some technical context. However, it does not explicitly state that it is a read-only operation, authentication requirements, or error behavior. This is adequate for a simple getter but not rich.

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, direct sentence with no unnecessary detail. The parenthetical endpoint adds useful technical context without bloating the text.

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 zero inputs and no output schema, the description adequately covers the purpose and high-level return content. It could be more explicit about the response structure, but the simplicity of the tool makes this acceptable.

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 accepts zero parameters, so the description has nothing to add beyond the empty schema. The mention of what is returned (profile and business info) helps set expectations, consistent with the baseline of 4 for zero-parameter tools.

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 retrieves the currently authenticated user's profile along with business information, and specifies the endpoint '/auth/me'. This specific verb+resource combination distinguishes it from sibling tools like gerent365_get_business and gerent365_get_employee.

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 referencing the 'currently authenticated user', making it clear when to use this tool (for the current session's profile). However, it does not explicitly mention alternatives or exclusion cases, so it falls 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?

No annotations are provided, so the description must convey behavior. The verb 'Consulta' indicates a read-only query, which is the key behavioral trait. However, it does not describe the return format or any error conditions, leaving some behavioral ambiguity.

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, front-loaded sentence that directly states the purpose without any redundant information.

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

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

The tool is simple with one parameter and no output schema. The description covers the core purpose but lacks details about the response structure or potential edge cases, making it minimally sufficient but not comprehensive.

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 single parameter weekStart is fully documented in the input schema with format YYYY-MM-DD, and the description adds no extra parameter semantics. Baseline of 3 applies due to 100% 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 uses a specific verb 'Consulta' and explicitly states the resource (weekly schedule publication status), distinguishing it from sibling tools like gerent365_publish_schedule and gerent365_get_schedule.

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 clearly implies the tool is for checking whether a week's schedule was published, which provides context for when to use it, but it does not explicitly name alternatives or exclusion criteria.

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 only states the basic function and parameter format, but does not disclose any behavioral aspects like authentication requirements, what the response contains, or whether it is a safe read-only 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 consists of two short, front-loaded sentences in Spanish. Every word adds value—the action, the resource, and the parameter format—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?

Given the tool's low complexity (one parameter, no output schema, no nested objects), the description is minimally sufficient but lacks detail on the return value and whether the schedule covers all employees. This could be important for an agent deciding if this tool meets a user request.

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

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

Schema coverage is 100% and the schema already describes weekStart as 'Inicio de la semana (YYYY-MM-DD)'. The description adds the note that weekStart is typically Monday, which provides slight contextual value beyond the schema but does not meaningfully expand parameter meaning.

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 ('Obtiene') and resource ('el horario de una semana'), clearly indicating a read operation for a weekly schedule. It distinguishes from sibling tools like gerent365_assign_shift and gerent365_copy_week because it explicitly focuses on retrieval of a schedule.

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 no guidance on when to use this tool versus alternatives such as gerent365_get_attendance or gerent365_assign_shift. It only states what the tool does, with no mention of when it is appropriate or when to prefer other 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?

With no annotations provided, the description carries the full burden. It discloses the authentication requirement (kioskCode + pin) and that it returns 'productos disponibles', but does not mention return format, error behavior, or side effects beyond the read-only verb 'Obtiene'. Some useful context is given, but it is not comprehensive.

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

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

The description is a single concise sentence that front-loads the main purpose and then adds authentication context without any waste. It is appropriately sized for the tool's simplicity.

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 simple schema, no annotations, and no output schema, the description covers the core intent and authentication requirement, but leaves ambiguity about how optional parameters interact with environment defaults and the exact meaning of 'productos disponibles'. It is minimally sufficient but not fully self-contained.

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 provides full descriptions for both parameters (100% coverage), so the baseline is 3. The description adds minimal value by noting they are used together for authentication, but does not clarify behavior around optionality (e.g., how env defaults apply). No further parameter details 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 clearly states the action ('Obtiene') and resource ('productos disponibles desde el kiosko'), specifying a distinct scope (kiosk) that differentiates it from the sibling gerent365_list_products. The authentication context further refines its purpose.

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

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

The description implies usage in a kiosk-authenticated context by mentioning 'autenticado con kioskCode + pin', but it does not explicitly state when to choose this over alternatives like gerent365_list_products or provide exclusions. The guidance is implied rather than explicit.

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

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

With no annotations provided, the description carries the burden of disclosing behavior. It mentions the optional GPS coordinates and the conditional managerCode for late punches, which adds useful context. However, it does not describe side effects, permissions, success/failure behavior, or return values, leaving transparency incomplete.

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

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

The description is extremely concise, consisting of two short sentences. It front-loads the main purpose and adds only essential detail, with no redundant information.

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 is adequate for basic understanding with a well-documented schema, but it lacks key context: no output schema exists, and the description does not mention return values, error conditions, or prerequisites (e.g., employee must exist). This leaves gaps for a mutation tool of moderate 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?

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining that GPS coordinates are optional and that managerCode may be required specifically for late punches, which enriches the schema's property 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 registers a time punch (fichaje) at the kiosk, enumerating the types (entrada, salida, descanso). This distinguishes it from sibling tools like get_attendance or get_last_punch, which are read-only.

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 establishes clear usage context: this tool is for recording punches at the kiosk. However, it does not explicitly mention when not to use it or point to alternatives for viewing/validating punches, so it falls 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool validates and returns status/next action, which implies a read-only operation, but it does not explicitly state side effects, authentication requirements, or error behavior. This is a moderate level of transparency, not a complete disclosure.

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, well-structured sentence that is front-loaded with the action and resource, followed by the output. Every word contributes value, with no redundancy or filler. It is 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?

With no output schema, the description partially explains the return value (status and next action) but not the full structure. The tool has only two optional parameters and is relatively simple, so the description is adequate but leaves gaps about error handling, whether it mutates data, and the exact response format. This makes it minimally viable.

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 has full coverage (100%) with descriptions for both parameters (pin and kioskCode). The description only reiterates 'kioskCode + pin' without adding additional meaning or format details. Baseline of 3 is appropriate as the schema handles the 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 the action ('Valida un empleado en el kiosko'), the resource (employee at kiosk), the required inputs (kioskCode + pin), and the output (status and next available action). This distinguishes it from sibling tools like kiosko_punch, which likely performs the action rather than validating.

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 validating before a kiosk action, but it does not explicitly state when to use this tool vs alternatives like kiosko_punch or get_employee. There is no exclusion or alternative named, so usage context is only implied by the nature of the tool (validation vs action).

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 present, so the description must carry the full burden. It states a simple list operation, implying a safe read, but does not disclose pagination, ordering, or return format. For a zero-parameter list, this is minimally adequate but lacks behavioral details beyond the obvious.

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

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

The description is a single, concise Spanish sentence that directly conveys the action. It is appropriately sized and front-loaded with the key information, with no wasted words.

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

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

Given the low complexity (no params, no output schema), the description is adequate but misses the opportunity to differentiate from gerent365_search_customers or mention ordering/pagination. Since there is no output schema, the agent receives no guidance on the shape of returned data, so completeness is moderate.

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

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

There are zero parameters, and the schema is empty, so baseline 4 is appropriate. The description adds no parameter information because none 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 uses a specific verb ('Lista' = lists) and resource ('clientes' = customers), clearly indicating a read operation that returns business customers. It distinguishes from siblings like search_customers (which implies filtering) and create/update customers. Although it doesn't explicitly say 'all', it is clear enough.

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 no guidance on when to use this tool versus alternatives like gerent365_search_customers. It does not mention filtering capabilities or imply any specific use case beyond listing all customers, so no context or exclusions are provided.

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

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

No annotations are present, so the description carries the burden. It discloses that the tool lists all employees, which implies a read-only operation. However, it does not add details like pagination, response format, or any side effects, though for a simple list tool these may be less critical.

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

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

The description is a single, concise sentence that is front-loaded with the verb and object. Every word earns its place, with no unnecessary 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?

With no output schema and no annotations, the description should compensate by explaining what the response contains or any caveats. It only says 'lists all employees of the business,' leaving the agent without knowledge of the return structure or any potential limitations.

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

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

The input schema has zero parameters, so there is nothing to document. The description adds no parameter info, but none is needed; baseline 4 applies per rubric for 0-parameter tools.

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 the specific verb 'Lista' (lists) and states the resource 'todos los empleados del negocio' (all business employees). This clearly distinguishes from the sibling get_employee which targets a single employee, and from create/update/delete employee 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?

Usage is implied by the verb 'list' versus 'get' in sibling tools, but the description does not explicitly state when to use this instead of get_employee or provide any exclusions. It gives clear context but no explicit alternative 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 implies a read-only operation with the verb 'Lista' and specifies the scope ('del negocio'), but it does not disclose details such as whether all job positions are included (e.g., active only), ordering, or response structure. The description is sufficient for a simple list operation but lacks explicit behavioral traits beyond the core function.

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 clear sentence that is front-loaded with the main action and resource. It is concise with no redundant words or filler, effectively conveying the purpose in minimal space.

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, no annotations), the description is largely complete for an agent to understand when to use it. It states what it returns (list of job positions with hourly rates) and the scope. Minor gaps include not specifying the exact fields returned or any filtering behavior, but these are not critical for a basic list operation.

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

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

The tool has zero parameters, which is the baseline for a score of 4. The description does not need to specify parameter semantics because there are none, and the schema confirms an empty object.

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

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

The description clearly states that the tool lists job positions (JobPosition) from the business, including their hourly rates. The verb 'Lista' is specific and the resource is unambiguous, distinguishing it from sibling tools like create_job_position, update_job_position, and delete_job_position.

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 context that this tool is for listing job positions, but it does not explicitly mention alternatives or when not to use it. Since the sibling tools include create/update/delete operations, usage is implied rather than explicitly guided.

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

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

No annotations are provided, so the description carries full behavioral burden. The verb 'Lista' implies a read-only operation, but the description doesn't explicitly state non-destructive behavior, authentication requirements, or return format details, leaving some ambiguity for a tool that could have side effects (though it likely doesn't).

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

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

The description is two short sentences: the first states the main purpose with a specific verb and resource, and the second explains the optional filter. It is front-loaded, concise, and contains no unnecessary information.

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 operation with only one optional parameter and no output schema, the description is reasonably complete. However, it doesn't specify the response structure, whether results are paginated, or any preconditions like authentication, and with no annotations to fill the gap, it falls short of being fully contextual.

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 provides 100% coverage for the single 'status' parameter with a description and enum values. The description repeats the filtering capability without adding new meaning beyond what the schema already says, so it earns the baseline score for high schema coverage without additional semantic contribution.

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

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

The description clearly identifies the action ('Lista') and the resource ('periodos de nómina'), making it obvious what the tool does. It distinguishes itself from sibling payroll tools like create_payroll_period, calculate_payroll, approve_payroll, and pay_payroll, which perform different actions.

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 a listing/querying use case with an optional status filter, but it doesn't explicitly state when to use this tool versus alternatives or mention any exclusions. It provides clear context but lacks explicit guidance on when to prefer this over other payroll period 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 of behavioral disclosure. It only states that it lists categories, but doesn't mention any behavioral traits such as read-only nature, authentication requirements, pagination, sorting, or whether inactive categories are included.

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

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

The description is a single sentence that immediately presents the action and resource. It is appropriately sized for a tool with no parameters, with no unnecessary words 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 low complexity (0 parameters), the description is adequate but has gaps. The absence of an output schema means the agent doesn't know what fields or shape the category list returns, and the description doesn't provide that information. It's a minimal but not fully complete description.

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 schema documents this completely. Per the rubric, a baseline of 4 is appropriate because there are no parameters to explain, and the description doesn't need to compensate for missing parameter information.

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 the specific verb 'Lista' and clearly identifies the resource 'categorías de productos del negocio', distinguishing it from siblings like gerent365_list_products (which lists products, not categories) and gerent365_create_product_category (which creates, not lists).

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 does not explicitly state when to use this tool versus alternatives, but the verb 'Lista' implies its use for retrieving product categories. No exclusions or alternative tools are mentioned, so guidance is 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?

With no annotations, the description carries the full burden of behavioral disclosure. It implies a read-only list operation but provides no details about return format, pagination, ordering, authentication requirements, or any potential side effects. This is a minimal disclosure.

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

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

The description is a single concise sentence in Spanish with no wasted words. It is appropriately front-loaded and easy to scan.

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

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

Given the low complexity (no parameters, no output schema, no annotations), the description is adequate but sparse. It omits any information about what the returned product list contains or whether it is paginated. While acceptable for a simple tool, it leaves gaps that a richer description could fill.

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 schema coverage is 100% (vacuously). The description doesn't need to elaborate on parameters, and the baseline of 4 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 states a clear action ('Lista los productos') and resource ('del negocio'), which distinguishes it from siblings like create_product and list_product_categories. The verb and object are specific and unambiguous.

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

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

No guidance is provided on when to use this tool versus alternatives such as gerent365_kiosko_products or list_product_categories. The description simply states what it does without any contextual or conditional advice.

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 present, and the description gives no insight into behavior such as sorting, pagination, return format, or permissions. It only states that it lists reservations, which is minimal.

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

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

The description is two short, clear sentences with the primary action front-loaded. Every word 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 two optional parameters and no output schema, the description is adequate but incomplete. It fails to mention the status filter from the schema and does not describe the response format, so it leaves some uncertainty.

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% since both parameters have descriptions. The tool description adds no extra semantics beyond the schema, 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 clearly states the tool lists business reservations with a specific verb and resource. It is easily distinguishable from sibling tools like create_reservation or update_reservation.

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 mentions the ability to filter by date, providing some context for when to use the date parameter. However, it does not mention alternative tools or when not to use it, so guidance is limited.

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. The verb 'lista' implies a read-only operation, but there is no explicit statement about safety, authorization, pagination, or what data is returned. It is minimally transparent but not misleading.

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, short, front-loaded sentence with no wasted words. It effectively communicates the tool's purpose without unnecessary elaboration.

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 and no output schema, the description is adequately complete. It clearly identifies the resource (business tables) and the action (list). However, it could benefit from mentioning what the output contains or specifying the domain (restaurant tables) to further disambiguate, but it is not critically incomplete.

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

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

The tool has zero parameters, and the schema is an empty object with 100% coverage. Per guidelines, a 0-parameter tool is baseline 4, and the description needs to add no parameter semantics since there are none.

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 'Lista las mesas del negocio' uses a specific verb ('lista') and resource ('mesas del negocio'), clearly indicating it lists the business's tables. This distinguishes it from the sibling tool 'gerent365_create_table', which creates tables.

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

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

No usage guidance is provided. The description does not state when to use this tool versus other list tools, nor does it specify any exclusions or alternative tools. The user must infer that it is used when needing to list tables, but no explicit context is given.

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 of behavioral disclosure. It discloses that the tool lists requests and supports filtering, but it does not mention scope (e.g., whether it returns all requests or only the current user's), potential permissions, or return format details. This is a gap for 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 a single, concise sentence with front-loaded information: it states the primary action and then the filtering capability. Every word is necessary, and there is no wasted language.

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 one optional parameter, the description is largely adequate. It explains what the tool does and mentions the filter. However, it lacks explicit detail about the output structure or ownership scope, which could be important in a complete context. Given the low complexity, this is a minor gap.

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 has 100% coverage for the single optional parameter 'status', including its possible values in the schema description. The tool description adds no new meaning beyond the schema, 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 clearly states the verb 'Lista' (lists) and the resource 'solicitudes de ausencia' (absence requests), making the tool's purpose explicit. It also mentions the optional status filter, distinguishing it from sibling tools like create_time_off and update_time_off.

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 context that the tool lists absence requests and can be filtered by status, which informs the use of the optional parameter. However, it does not explicitly name alternatives or state when not to use this tool, but its list nature and resource specificity make the usage straightforward.

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 only states 'list' which implies read-only, but it does not disclose any additional behavior such as whether only active tip pools are returned, sorting, or permission requirements.

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 short sentence that is front-loaded with the verb and resource. It contains no unnecessary words 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 simplicity of the tool (no parameters, no output schema, no annotations), the description is minimally adequate. However, it does not specify the return format or any filtering/sorting behavior, leaving some ambiguity for the agent.

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

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

The input schema has zero parameters, so there is nothing to describe. Schema coverage is 100% (vacuously), and for a zero-parameter tool the baseline is 4, which is appropriate here.

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 'Lista los pools de propinas (tip pools) del negocio' clearly identifies the action (list) and the resource (tip pools) with a business scope. It distinguishes from sibling tools like create_tip_pool and distribute_tips due to the verb 'lista' and resource specificity.

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 no guidance on when to use this tool versus alternatives. It only states the action without mentioning prerequisites, exclusions, or related tools such as create_tip_pool, leaving the usage context entirely 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 burden of disclosing side effects. It explicitly states the session cookie persistence and the env var fallback, which are key behavioral traits. It does not mention error handling or re-login behavior, but the essential side effect is covered.

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 action, then the session side effect and the env var fallback. Every sentence earns its place with no 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?

For a simple login tool with no output schema and no annotations, the description covers the purpose, side effect, and parameter fallback adequately. It lacks details about return values, but that is not required given the minimal 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 input schema already provides 100% parameter descriptions, including the optionality and env var fallback. The description adds little beyond confirming the login purpose, 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?

The description clearly states the login action ('Inicia sesión en Gerent365 con email y contraseña') and differentiates it from sibling tools by mentioning the session cookie storage for subsequent operations. This is a specific verb+resource with a clear scope.

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 as a prerequisite by stating it saves session cookies for other tools, and clarifies the credential fallback to environment variables. It lacks explicit exclusion of alternatives, but the context is clear enough for a login 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?

No annotations are provided, so the description carries the burden. It discloses the main behavior (closing the session) and an additional side effect (clearing cookies), but does not discuss other implications like token invalidation, error cases, or prerequisites.

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 concise sentence, front-loaded with the verb and resource, no filler. It 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 zero-param logout tool, the description is adequate but lacks details on preconditions or side effects beyond cookies. It doesn't mention return value, but that is often empty for such actions. Given no annotations, a few more details would make it 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 takes no parameters, so schema coverage is 100% and there are no parameter semantics to explain. The baseline score of 4 is appropriate since the description appropriately avoids any param details.

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 closes the current Gerent365 session and cleans cookies, with a specific verb and resource. It is unambiguous and distinguishes from sibling tools like login.

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 by stating its action, but provides no explicit guidance on when to use it vs alternatives or any exclusions. Users must infer that it's for ending a session.

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 only states that a payroll period is marked as paid but does not disclose consequences (e.g., irreversibility, triggering of payments), required prior states, or any side effects. This is insufficient for a state-mutating 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 a single, clear, front-loaded sentence with no redundant words. It is appropriately concise for a simple one-parameter tool, though slightly terse in terms of broader context.

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

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

The tool is part of a payroll workflow with sibling tools like calculate and approve, but the description does not explain where 'marking as paid' fits in that workflow. It lacks any mention of required prior state (e.g., must be approved), return values, or error conditions, making it incomplete for an agent to use confidently.

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% (the 'id' parameter is described as 'ID del periodo de nómina'). The description adds no additional parameter semantics beyond the schema, 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 uses a specific verb ('Marca' / marks) and resource ('periodo de nómina' / payroll period), and the phrase 'como pagado' clearly indicates the state transition. This distinguishes it from sibling tools like gerent365_calculate_payroll and gerent365_approve_payroll.

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

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

No guidance is provided on when to use this tool or how it relates to alternatives. The description does not mention prerequisites (e.g., approval required), the payroll workflow, or any exclusions, leaving the agent to infer the appropriate context.

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 of behavioral disclosure. It does disclose a key side effect: 'notifica a los empleados activos' (notifies active employees). However, it does not mention whether the operation is irreversible, whether it overwrites an existing published schedule, or any permission requirements, leaving important behavioral gaps.

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

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

The description is a single sentence that is concise, front-loaded with the primary action, and includes the important notification side effect. Every word contributes value; there is no fluff 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?

This is a simple tool with one parameter and no output schema, and the description covers the core action and a key side effect. It is missing a little context around the publishing lifecycle (e.g., whether it can be redone, how to verify success via gerent365_get_publish_status), but for a low-complexity tool this is largely sufficient.

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

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

Schema description coverage is 100% for the single required parameter 'weekStart', with the description 'Semana a publicar (YYYY-MM-DD)' already conveying the format and purpose. The tool description adds no additional semantic detail beyond that, so it meets the baseline without enhancing parameter understanding.

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: 'Publica el horario de una semana y notifica a los empleados activos' (publishes a week's schedule and notifies active employees). This distinguishes it from sibling tools like gerent365_get_schedule, gerent365_assign_shift, and gerent365_copy_week by specifying a publish-and-notify behavior.

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

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

No explicit guidance is given about when to use this tool versus alternatives. It does not mention prerequisites (e.g., schedule must exist or weekStart must be a particular day), nor does it state when not to use it or point to related tools like gerent365_get_publish_status.

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 hay anotaciones, por lo que la descripción debe cargar con la transparencia. Se menciona el rango de fechas opcional, lo cual es un comportamiento útil, pero no se detalla qué contiene el reporte, el formato de respuesta, ni si requiere permisos especiales. La naturaleza de solo lectura se infiere por 'Obtiene', pero falta contexto adicional.

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?

La descripción es una sola oración con información esencial al frente: qué hace y el parámetro clave. No hay palabras superfluas y es fácil de escanear.

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?

La herramienta tiene solo 2 parámetros opcionales y no hay esquema de salida ni anotaciones. La descripción cubre lo básico, pero no especifica el contenido del reporte, el formato de respuesta, ni proporciona contexto sobre cómo se diferencia de herramientas hermanas como 'gerent365_dashboard_stats'. Para un agente que necesita seleccionar correctamente, falta información.

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?

El esquema ya cubre el 100% de los parámetros con descripciones. La descripción añade valor al indicar que ambos parámetros forman un rango de fechas opcional, lo que no se explicita en el esquema. Este matiz compensa la información ya presente.

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?

La descripción indica claramente que obtiene el reporte del dashboard y que es un resumen de métricas. La acción 'Obtiene' y el recurso 'reporte del dashboard' son específicos. Sin embargo, no diferencia explícitamente de herramientas hermanas como 'gerent365_report_sales' o 'gerent365_dashboard_stats', por lo que no alcanza el nivel 5.

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

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

No se proporciona ninguna guía sobre cuándo usar esta herramienta frente a alternativas. Solo se describe qué hace, sin mencionar exclusions, preferencias o cuándo no usarla. El uso se infiere débilmente, pero no hay indicación explícita de diferenciación con otras herramientas de reportes.

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 must carry full behavioral disclosure. It implies a read-only operation via 'Obtiene' but does not mention return format, pagination, permissions, or potential side effects, which are critical for an agent to invoke it safely.

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

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

The description is a single concise sentence, front-loaded with the action and resource, with no unnecessary words or repetition of schema details.

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?

Despite being a simple read tool, the description lacks essential context: no output format, no details on what the report includes, no handling of edge cases, and no mention of whether the range is inclusive. This leaves significant ambiguity for an agent, especially given the absence of an output 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 input schema provides 100% coverage for both parameters with descriptions and format (YYYY-MM-DD), meeting the baseline for parameter semantics. The description's mention of a date range reinforces the schema but adds no additional meaning about parameter relationships or validation.

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

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

The description clearly identifies the tool as retrieving the business's sales report for a date range, using the specific verb 'Obtiene' and the resource 'reporte de ventas del negocio'. It distinguishes itself from sibling report tools like gerent365_report_dashboard by focusing on sales, though it doesn't explicitly mention alternatives.

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

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

No guidance is provided on when to use this tool versus other reporting or data retrieval tools. The description simply states the action without context, prerequisites, or exclusions, leaving the agent without clear decision support.

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 burden. It discloses which fields are searched but omits behavioral details like case sensitivity, partial match behavior, result limits, sorting, or return format. This is a significant gap for a search tool.

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, front-loaded sentence that conveys the core purpose and scope with no unnecessary words. It effectively uses the parenthetical to list searchable fields.

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 (one parameter, no output schema), the description is minimally viable for invocation. However, it does not explain what the tool returns (e.g., full customer objects, IDs, pagination), leaving some ambiguity.

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 q as 'search term' with 100% coverage. The description adds value by explaining that the term matches name, phone, and email, providing useful context beyond 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 tool searches customers by text and specifies the fields (name, phone, email). This distinguishes it from sibling tools like list_customers (which likely lists all) and create/update_customer.

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 usage is implied by the description: use it when you need to find customers by name/phone/email. However, it does not explicitly mention when not to use it or mention alternatives such as list_customers for retrieving all customers.

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 discloses that all fields are optional and only provided ones are sent ('solo se envían los provistos'), which is a useful partial-update behavior beyond the schema. However, with no annotations, it does not address permissions, side effects, or response format, leaving some behavioral ambiguity for a mutation tool.

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

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

A single, front-loaded sentence that fully explains the core behavior without unnecessary words. Efficient 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?

The tool has 9 parameters including a nested settings object, no output schema, and no annotations. The description provides the key behavior (partial update) and the schema covers parameters, but it lacks usage context, error handling, and any mention of permissions or return values. Adequate for a simple update, but not comprehensive.

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?

Input schema has 100% coverage, so all 9 parameters are described individually. The description adds no parameter-specific semantics beyond noting optionality, which is already reflected in required:0. 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?

The description clearly states the tool updates business information ('Actualiza la información del negocio'), using a specific verb and resource, and distinguishes from sibling update_* tools by targeting the business entity. While it doesn't enumerate specific fields, the name and schema clarify scope.

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

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

There is no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or relationship to other update tools (e.g., update_customer, update_employee). The context signals show 51 sibling tools, but the description provides no selection criteria.

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 of behavioral disclosure. It only states that the tool updates a customer, but fails to mention important behaviors such as partial vs. full update, error handling for non-existent IDs, return values, or authentication requirements.

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

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

The description is a single, concise sentence that front-loads the core action and resource. There is no wasted wording, and it is appropriately brief for the basic purpose, even though it lacks depth in other areas.

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 has 11 parameters, no output schema, and no annotations, this one-sentence description is insufficient. It provides no information about which fields can be updated, return structure, error behavior, or prerequisites, leaving significant gaps for an agent to invoke the tool correctly.

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

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

The schema description coverage is only 9%, with only 'id' documented. The description does not compensate for the other 10 parameters, offering no additional meaning beyond what the schema provides. It only reinforces 'id' as the identifier, which is already stated 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 tool's function: 'Actualiza un cliente existente por su ID' (Updates an existing customer by its ID). It specifies a specific verb (update), resource (customer), and identification method (by ID), distinguishing it from sibling tools like create_customer.

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

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

Usage is implied: the description indicates it is for updating existing customers, which distinguishes it from creation or listing tools. However, it provides no explicit when-to-use or when-not-to-use guidance, nor does it mention any prerequisites or 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 must disclose behavior. It reveals that only provided fields are updated (partial update), which is useful. However, it does not mention permissions, error handling, or the behavior if the employee ID does not exist, leaving significant behavioral gaps.

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, clear sentence with no redundancy. It efficiently communicates the action and the partial-update 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?

With 9 parameters, 1 required, low schema coverage, no annotations, and no output schema, the description is minimal. It does not explain return values, field constraints, or relationships between fields (e.g., position vs positionId), making it incomplete for an agent to use 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 description coverage is only 22%. The description does not elaborate on any parameter beyond saying that only provided fields are sent. Most parameters (e.g., role, email, positionId) lack explanatory context, so the description does not compensate for the low 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 'Actualiza los datos de un empleado existente' (updates data of an existing employee), which is a specific verb+resource. It distinguishes from siblings like create_employee and delete_employee.

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 does not mention when to use this tool vs alternatives. It only says 'Solo se envían los campos provistos' (only provided fields are sent), implying partial updates, but gives no explicit guidance on when to use it or what alternatives exist for PIN updates or other employee-related operations.

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 states only that the PIN is changed, without mentioning side effects, permissions, reversibility, or any impact on kiosk operations. The mutation behavior is clear but no additional context is provided.

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 entire description is a single, efficient sentence in Spanish. It is front-loaded with the verb and resource, with no wasted words.

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

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

Although the tool is simple, the description lacks usage context and behavioral details. It does not mention when to use it, what outcome to expect, or any operational impact. The absence of an output schema and annotations means the description should provide more context, but it does not.

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

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

Schema description coverage is 100% for both parameters ('id' and 'pin'), so the schema carries the semantic weight. The description adds no extra meaning beyond what is already in the schema, giving the baseline 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 the action ('Cambia' = changes), the specific resource ('PIN de fichaje (kiosko)'), and the target ('empleado'). It distinguishes this from the sibling 'update_employee' tool by focusing solely on the PIN.

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

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

No guidance is provided about when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or relationship to sibling tools like 'gerent365_update_employee' or 'gerent365_kiosko_validate'.

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 only states the action 'update' but does not disclose side effects, required permissions, behavior on non-existent IDs, or whether it is a partial or full update. This is insufficient for a mutation tool.

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, front-loaded sentence with no wasted words. It is concise and to the point, though it lacks detail that is penalized in other dimensions.

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 mutation tool with no annotations and no output schema, the description is severely incomplete. It does not explain updatable fields, return values, or any post-update behavior, leaving the agent with insufficient context.

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 only 14% (only 'id' is described), and the description adds no parameter information. With 7 parameters and no compensation from the description, parameter semantics are extremely poor.

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 'Actualiza un puesto de trabajo existente' uses a specific verb ('Actualiza') and resource ('puesto de trabajo existente'), clearly distinguishing it from sibling tools like create, list, and delete job positions.

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 modifying existing job positions, and sibling names (create/delete) provide clear context. However, it does not explicitly state when not to use it or mention alternatives, so it lacks explicit exclusions.

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 bears the full burden of behavioral disclosure. It states only that it updates fields (date, time, status), but does not disclose whether it performs partial or full updates, what happens to omitted fields, validation rules, or required authentication. This is a significant gap for a mutation tool.

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

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

The description is a single sentence that is front-loaded with the core action and resource. It is perfectly concise with no unnecessary words 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 an 8-parameter update tool with no output schema and no annotations, the description is too thin. It does not explain that only id is required, how omitted fields are treated, possible error scenarios, or return values. The context is far from complete for an agent to invoke it reliably.

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 only 25% (only id and status have descriptions). The description adds meaning for date, time, and status but ignores name, notes, phone, and partySize, which are also undocumented in the schema. It only partially compensates for the low 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 uses the specific verb 'Actualiza' (updates) and clearly identifies the resource as an existing reservation by ID. It distinguishes itself from sibling tools like create_reservation and list_reservations by stating it modifies an existing entity rather than creating or listing.

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

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

The description implies it is for updating existing reservations but provides no explicit guidance on when to use it versus alternatives, nor does it mention prerequisites like obtaining the ID via list_reservations. No exclusions or alternative tools are referenced.

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 only says 'actualiza su estado'. It does not disclose whether special permissions are required, whether the action is reversible, what side effects approval may have, or how rejectionReason affects the request. This is a significant gap for a mutating tool.

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, front-loaded sentence with no wasted words. The parenthetical 'actualiza su estado' reinforces the action without 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?

For a simple status-update tool, the description is minimally adequate but incomplete. It does not mention that status can be set to PENDING, nor when rejectionReason is relevant. With no output schema and no annotations, additional detail about expected behavior and edge cases would improve 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?

The input schema has 100% coverage with descriptions for all parameters, so the baseline is 3. The description itself adds little parameter-level meaning beyond mapping 'Aprueba o rechaza' to the status field, but the schema already documents id, status, and rejectionReason adequately.

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

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

The description states a specific action ('Aprueba o rechaza') and a concrete resource ('solicitud de ausencia'), clearly distinguishing this from sibling tools like create_time_off and list_time_off. However, it omits the PENDING status allowed by the schema, so it does not fully cover the tool's scope.

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

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

Usage context is implied: this tool updates the status of an existing time-off request, likely for approval/rejection workflows. There is no explicit guidance about when to use it over create_time_off or list_time_off, nor any mention of prerequisites or exclusions.

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