propose_create_invoiceCreate an invoice. Fortnox API POST /3/invoices (https://api.fortnox.se/apidocs). Only prepares the change for the person to approve; this tool sends NOTHING to Fortnox, and the answer says how the approved change is sent. Body: {"Invoice": {…}}; required: CustomerNumber.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | The request body, as Fortnox expects it: an object |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / body / anyOfPrevious value: -[
- {
- "additionalProperties": {},
- "propertyNames": {
- "type": "string"
- },
- "type": "object"
- },
- {
- "items": {},
- "type": "array"
- }
-]New value: +[
+ {
+ "additionalProperties": {},
+ "propertyNames": {
+ "type": "string"
+ },
+ "type": "object"
+ },
+ {
+ "items": {},
+ "type": "array"
+ },
+ {
+ "maxLength": 200000,
+ "type": "string"
+ }
+]Input schema / properties / body / descriptionPrevious value: -"The request body, as Fortnox expects it"New value: +"The request body, as Fortnox expects it: an object"Input schema / properties / body / anyOfAdded value: +[
+ {
+ "additionalProperties": {},
+ "propertyNames": {
+ "type": "string"
+ },
+ "type": "object"
+ },
+ {
+ "items": {},
+ "type": "array"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare openWorldHint=false and readOnlyHint=false, and the description corroborates/explains why: nothing leaves the process, the answer explains how the approved change is sent. That is genuine context beyond the annotations, though idempotency is left to the annotation rather than described.
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?
Three tight sentences, front-loaded with the action and endpoint, followed by the approval caveat and body hint. The API doc URL is mildly extraneous but does not crowd out the essential content.
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 need not be described, and the description covers the non-obvious parts: no network call, required body field, and what the response conveys. Only the downstream approval path is left implicit.
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 already 100%, and the description still adds value for a freeform body by giving the concrete wrapper shape {"Invoice": {…}} and the required CustomerNumber field, which the schema's generic "as Fortnox expects it: an object" does not 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?
States a specific verb and resource ("Create an invoice") plus the exact backing endpoint (POST /3/invoices), and the proposal framing separates it from direct-write siblings like execute_fortnox_write. An agent can tell instantly that this stages an invoice rather than performing one.
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?
Makes the crucial usage distinction explicit: it "only prepares the change for the person to approve" and "sends NOTHING to Fortnox." It does not name the follow-on sibling (resolve_fortnox_write / execute_fortnox_write) that actually commits the approved change, so the agent must infer the rest of the workflow.
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.