arquivo_baixarBaixa o arquivo (XML ou PDF/DANFE) de uma NF-e/NFC-e/NFS-e por chave de acesso. Retorna conteúdo em base64.
| Name | Required | Description | Default |
|---|---|---|---|
| Chaves | No | ||
| ChaveNF | No | ||
| FileType | No | Tipo do documento fiscal (Padrão 1 - XML) Valores: 1 - XML; 2 - DANFE | |
| Base64Logo | No | ||
| TipoDocumentoFiscal | No | Tipo do documento fiscal (Padrão 1 - Saída) Valores: 0 - Entrada; 1 - Saída |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the agent knows the tool is safe and idempotent. The description adds value by specifying the return format (base64) and the file types. It does not contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, directly stating the purpose and output format. It is front-loaded with the key action and resource. Every sentence is necessary and 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?
With five parameters, no required ones, and no output schema, the description is insufficient. It does not explain how to specify the access key (which of the two key parameters to use), the role of Base64Logo, or the behavior when parameters are omitted. The agent lacks guidance 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?
Schema description coverage is low (40%), and the tool description does not adequately compensate. It mentions file types (XML/PDF) which maps to FileType, but leaves Chaves, ChaveNF, and Base64Logo unexplained. The user must infer that ChaveNF is a single key, but the array parameter Chaves is ambiguous. No guidance on parameter combinations.
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?
Description clearly states the verb 'Baixa' (downloads) and specifies the resource as XML or PDF/DANFE of a NF-e/NFC-e/NFS-e by access key. It distinguishes from sibling tools like 'arquivo_baixar_evento' and 'arquivo_baixar_periodo' by emphasizing the input method (access key).
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 the user has an access key, but it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites. No guidance on when not to use it or which sibling tool to choose.
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 has a clearly distinct purpose, with thorough descriptions that clarify overlaps (e.g., cliente_consultar vs cadastro_consultar). Even similar operations like arquivo_baixar variants have explicit scope differences.
Most tools follow a noun_verb pattern (e.g., cliente_consultar, evento_cancelar, produto_criar), but a few deviate (e.g., 'health', 'cte_desacordo'). Overall consistent enough for easy recognition.
34 tools is high but justified given the complexity of fiscal document management across multiple document types (NF-e, NFS-e, CT-e, MDF-e, etc.) and required CRUD, events, and auxiliary operations.
The tool set covers create/read/update/delete for clients, products, and tax rules, plus emission, cancellation, correction, and status checks for various documents. Minor gaps like dedicated NFS-e cancellation are handled by generic event tools.