ISR mensual de nomina (LISR art. 96) sobre una base gravable, para una fecha. Cuesta NOMINA. Declara la tabla y su vigencia; si la fecha cae fuera de la tabla cargada, no calcula y lo advierte. Resultado matematico, no resolucion oficial.
| Name | Required | Description | Default |
|---|---|---|---|
| base_gravable | Yes | ||
| fecha_calculo | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and does so well: it discloses the NOMINA cost, the edge case of dates outside the loaded table, and the caveat that the result is mathematical, not an official resolution. It does not explain authentication or rate limits, but for a calculation tool this is mostly sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences communicate purpose, cost, edge-case behavior, and result caveat. Every sentence carries distinct information and the most relevant facts are front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers inputs, date-dependent behavior, billing, and output nature. Since there is no output schema, the exact return shape remains slightly unclear, but the tool is low-complexity and the core invocation details are present.
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 maps both parameters conceptually: 'base gravable' and 'para una fecha'. However, schema description coverage is 0%, and the description does not compensate fully by explaining the expected date format or what an empty fecha_calculo default means.
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 identifies the exact calculation: monthly payroll ISR under LISR article 96 on a taxable base for a date. This clearly distinguishes it from siblings like calcular_imss and calcular_laboral. It lacks an explicit verb, relying on the tool name and noun phrases, so it is not a perfect 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?
The description establishes a clear usage context: payroll ISR calculation on a taxable base for a date, and notes the cost in NOMINA credits. It does not explicitly mention alternatives or exclusion rules, but the domain-specific framing is enough to route an agent appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools fall into clear families such as validar_*, verificar_* and consultar_*, but there is semantic overlap among consultar_catalogo, catalogo_leyes and catalogo_servicios, and between acreditar_fondeo and verificar_pago since both process CEP XML. The descriptions usually clarify the intent, but an agent could still choose the wrong generic catalog or payment tool.
The dominant pattern is Spanish infinitive_noun, e.g. validar_rfc, verificar_empresa and consultar_saldo, but there are noticeable deviations such as catalogo_leyes, estado_servicio, tipo_cambio and verificacion_completa. The English-style screening_listas and screening_monitorear also break the Spanish verb pattern, making the naming readable but inconsistent.
With 30 tools, the server sits well above the recommended MCP range and will add significant context/selection overhead. The broad multi-domain scope explains some of the size, but several account/meta tools could be consolidated, and the overall surface feels heavier than ideal.
The core workflows are well covered: company/invoice/payment verification, legal search and lookup, fiscal calculations, identity validations, screening and constancy validation are all present. However, there are dead ends: crear_fondeo_x402 requires an out-of-band REST liquidation step, screening_monitorear has no management/removal counterpart, and registrar_obligacion has no list/delete tools.