Prepare ARCA invoice

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 does disclose two important behaviors: it never issues the invoice, and it uses a specific authentication method (direct HTTP with optional browser fallback). However, it does not mention side effects such as creating a prepared record that can later be discarded or queried via sibling tools, nor does it mention any state changes or permissions required. While it covers the critical non-issuance aspect, it leaves out other relevant behaviors, making it only partially transparent.

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

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

The description is three sentences long and front-loads the core purpose immediately. The first sentence states what the tool does, the second covers authentication behavior, and the third gives the crucial workflow requirement. There is no redundant phrasing, and every sentence adds information. This is a model of concise, well-structured documentation.

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

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

Given the tool's complexity (10 parameters, 8 required, no output schema, no annotations), the description is far too sparse. It does not explain what a 'Factura C' is, what the expected input formats are (even though the schema provides patterns, the description doesn't guide usage), or what the tool returns or produces. It also doesn't mention how this prepared invoice relates to sibling tools like arca_discard_prepared_invoice or arca_invoice_status. An agent would be left guessing about many essential details needed to call 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 has 10 parameters (8 required) with 0% description coverage, meaning no field descriptions exist in the schema. The tool description provides no information about any parameter: it does not explain what 'receiverCuit', 'emissionDate', 'paymentMethods', etc., mean, nor their formats or relationships. Since the description is the only source of parameter semantics and it says nothing, this is a major gap. Score 1 is appropriate because the description adds no value whatsoever for understanding the parameters.

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

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

The description clearly states the tool's purpose: 'Prepare a Factura C through direct HTTP calls to official ARCA RCEL.' It specifies the verb (prepare), the resource (Factura C), and the method (direct HTTP calls). It also explicitly says 'This tool never issues the invoice,' which distinguishes it from the sibling arca_issue_invoice. This is a specific, non-tautological purpose that an agent can act on.

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

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

The description gives explicit workflow guidance: 'Show the preview and obtain explicit approval before calling arca_issue_invoice.' This tells the agent when to use this tool (preparation) and the required next step. It also mentions authentication modes ('direct HTTP by default, with browser fallback only when explicitly configured'), which is a usage context. It doesn't explicitly compare to all siblings (e.g., arca_list_invoices or arca_discard_prepared_invoice), but it clearly differentiates from the issuance tool, which is the primary alternative.

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