Ficha de una persona por CUIT/CUIL: identidad, condición fiscal AFIP (monotributo/responsable inscripto/autónomo, categoría y actividad declarada cuando es actor económico) y todas sus empresas argentinas vinculadas con los roles que ocupa en cada una. Cuesta 1 crédito.
| Name | Required | Description | Default |
|---|---|---|---|
| cuit | Yes | CUIT/CUIL de la persona, 11 dígitos |
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 behavior: the cost of 1 credit, and it details the content scope (identity, tax condition, linked companies with roles). However, it does not explicitly state that this is a read-only operation, nor does it describe response format, error conditions, or any authorization requirements. It adds moderate context but lacks full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single compact sentence that front-loads the tool's purpose, then uses a colon to list contents, and ends with the cost. Every clause adds value: the resource, the data categories, the condition ('cuando es actor económico'), and the credit cost. No fluff, 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 lookup tool with one parameter, no annotations, and no output schema, the description covers the essentials: what it returns (identity, tax status, linked companies/roles), the conditional fiscal data, and the cost. It does not describe the exact response structure, but that is partially mitigated by the content list. The absence of an output schema makes the description the primary source of expected data, and it provides a clear overview.
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 only parameter 'cuit' is already fully described in the schema (11 digits). The description mentions 'por CUIT/CUIL' but adds no additional semantics, format details, or default behavior beyond the schema. Baseline 3 applies since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific resource ('Ficha de una persona por CUIT/CUIL') and enumerates the exact content: identity, AFIP tax status, and linked companies with roles. This clearly distinguishes it from sibling tools like 'ficha_empresa' (company record) and 'buscar_empresas' (search). The verbiage is action-oriented and leaves no ambiguity about what the tool returns.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage: when you have a CUIT/CUIL and need a person's fiscal identity and companies. However, it does not explicitly state when to prefer this over siblings, nor does it provide exclusions or conditions (e.g., 'use this when you need AFIP status, not for general search'). The cost note ('Cuesta 1 crédito') is a qualifier but not a usage guideline.
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.
Each tool targets a distinct entity or action: searches for people, companies, importers, and tenders are clearly separated, as are company and person detailed profiles, credit balance, and autocomplete. The two overlapping-looking tools (buscar_empresas and sugerencias) differ in purpose: full search vs. lightweight autocomplete, so no real ambiguity exists.
Tool names follow a clear pattern: buscares use verb_noun, fichas use noun_noun, and saldo_creditos/sugerencias are standalone nouns. This is mostly consistent and predictable, with minor deviation from a strict verb_noun pattern.
With 8 tools, the server is well-scoped for its purpose of retrieving Argentine business data. It covers multiple search domains, detailed profiles, account management, and autocomplete without excessive fragmentation or unnecessary tools.
The core domain is well covered: search for companies, people, importers, and tenders, plus detailed profiles for companies and people. A minor gap is the lack of detail views for individual importers or tenders beyond search results, but agents can typically work around this with the existing search capabilities.
