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

Annotations already declare readOnlyHint=false, openWorldHint=false, idempotentHint=true, and destructiveHint=false. The description adds materially useful behavior beyond those annotations: the tool performs no Fortnox write, requires human approval, and the response explains how the approved change is sent.

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 compact and front-loaded: purpose, endpoint, approval-only behavior, body shape, and required fields appear in order with little wasted text. The API URL is justified by the tool's Fortnox-specific nature.

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 that annotations cover the safety profile and an output schema exists, the description is largely complete: it explains the prepare-only workflow and body requirements. The main remaining gap is explicit differentiation from the supplier-invoice file-connection sibling.

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, but the description adds real semantic value by specifying the Fortnox body envelope and the required body fields FileId, VoucherNumber, and VoucherSeries. It does not mention the financialyear parameter, though that parameter is already documented 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 states a specific verb and resource ('Create a voucher file connection') and identifies the underlying Fortnox endpoint. It is clear, but it does not explicitly distinguish this from the very similarly named sibling propose_create_supplier_invoice_file_connection, so it falls short of full sibling 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 gives clear usage context: it only prepares a change for human approval and sends nothing to Fortnox. It does not explicitly name alternatives or when-not to use it, such as propose_create_voucher or execute_fortnox_write, but the propose-only role is well conveyed.

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