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

Annotations declare readOnlyHint=false/idempotentHint=true, but the description adds the crucial trait the annotations cannot convey: no network call reaches Fortnox, so the effect is a pending proposal rather than a live mutation. It also discloses that the response tells the caller how the approved change is delivered. Missing is whether the proposal can be edited or discarded before approval.

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 no-side-effect statement sits in the middle where it earns attention, and the body shape is placed last as a calling hint. The endpoint URL with docs link is slightly boilerplate but short enough not to bloat the definition.

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?

An output schema exists, so return values needn't be described, and the propose-vs-send behavior is covered. However, for a create tool with an unconstrained free-form body, the description never indicates what the connection needs (which file, which supplier invoice), leaving a real gap an agent must guess at.

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 only one parameter exists (baseline 3), but the description goes further by showing the required wrapper shape {"SupplierInvoiceFileConnection": {…}}, which the free-form body schema does not convey. It does not enumerate which fields belong inside the wrapper (e.g. file id / invoice number), which would have been necessary for correct invocation.

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 gives a specific verb ('Create') and resource ('supplier invoice file connection'), names the underlying Fortnox endpoint, and clarifies the governing mechanic — it only prepares a change for approval. It never names its nearest sibling (propose_create_voucher_file_connection) or contrasts with execute_fortnox_write/upload_to_fortnox, so sibling differentiation is left to the name prefix.

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?

'Only prepares the change for the person to approve; this tool sends NOTHING to Fortnox' clearly establishes when this tool applies versus a real write, and notes the answer explains the send path. It stops short of explicitly naming the alternative tools (execute_fortnox_write, upload_to_fortnox) that an agent would otherwise consider.

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