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

Beyond the annotations, it discloses that the call has no external effect, that the response explains how the approved change will be sent, and the non-obvious Fortnox accounting quirk that rows carry net in Total and Fortnox itself adds VAT and payable rows. That is exactly the kind of behavior an agent could not infer from readOnlyHint/destructiveHint/idempotentHint.

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?

Front-loaded with purpose, then API reference, then the row-modeling caveat, then the approval caveat, then body shape — every sentence carries information. It is dense and slightly run-on with nested parentheses and semicolons, which costs it a point on readability.

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 one-parameter proposal tool with an output schema available, the description covers everything an agent needs: the wrapper envelope, the required field, the row semantics, and the fact that nothing is transmitted. No material gap remains.

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 only says the body is a generic object/array/string, so the description carries real weight by fixing the envelope shape {"SupplierInvoice": {…}} and naming SupplierNumber as required. It also explains how line rows must be constructed, which is meaning the schema cannot convey.

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?

Names a specific verb and resource (create a supplier invoice) and warns that it is really a proposal that sends nothing to Fortnox, which meaningfully separates it from execute_fortnox_write and resolve_fortnox_write. It stops short of distinguishing itself from near-siblings such as propose_create_supplier_invoice_file_connection or propose_bookkeep_supplier_invoice.

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 approval-flow framing ("Only prepares the change for the person to approve") tells the agent the correct context for calling it and implies the execute step is handled elsewhere. It does not explicitly name the alternative tool to use when a direct write or a different proposal type is needed.

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