Skip to main content
Glama
Sign In

More AI - ChatGPT & Claude MCP (Fortnox)

by cloud.amore.accounting
OverviewDiscussionsAdmin

Create a customer

propose_create_customer
Idempotent

Create a customer. Fortnox API POST /3/customers (https://api.fortnox.se/apidocs). Country is read-only: send CountryCode, the two-letter country code (SE for Sweden); Fortnox fills in the country name. 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: {"Customer": {…}}; required: Name.

Input Schema

NameRequiredDescriptionDefault
bodyNoThe request body, as Fortnox expects it: an object

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / body / anyOf
      Previous 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"
+  }
+]
    • changedInput schema / properties / body / description
      Previous value: -"The request body, as Fortnox expects it"New value: +"The request body, as Fortnox expects it: an object"
  2. Changed1 schema field changed
    • addedInput schema / properties / body / anyOf
      Added value: +[
+  {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  {
+    "items": {},
+    "type": "array"
+  }
+]
  3. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, idempotentHint=true; the description adds the far more important fact that no HTTP call is made and the answer explains how approval is dispatched. It also discloses the country-name derivation behavior. Minor gaps remain: it does not explain the idempotency claim or where the pending proposal is stored/discarded.

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

Conciseness4/5

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

Front-loaded with the action and the no-write guarantee, and every sentence carries information (endpoint, safety, country quirk, body shape, required field). A few sentences are run-on and pack multiple ideas, which slightly hurts scannability.

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

Completeness5/5

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

With an output schema present, return values need not be described, and the description still points to where the answer explains dispatch. Body wrapper, required field, read-only country handling, and proposal semantics cover everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema's single parameter is an opaque anyOf body described only as 'as Fortnox expects it: an object', which conveys almost nothing. The description compensates fully by giving the envelope shape {"Customer": {…}} and the required field Name, plus the CountryCode convention.

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

Purpose5/5

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

Names a specific verb and resource (create a customer) and pins it to the exact upstream endpoint (POST /3/customers). Immediately clarifies that the tool only proposes the creation for approval, which is the crucial distinction from execution siblings like execute_fortnox_write or resolve_fortnox_write.

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

Usage Guidelines4/5

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

The description makes the usage context unmistakable: it prepares a change for a human to approve and sends nothing to Fortnox, so an agent knows this is the safe pre-step. It stops short of naming the specific sibling that executes the approved change (execute_fortnox_write / resolve_fortnox_write), leaving the next step to inference.

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

All More AI - ChatGPT & Claude MCP (Fortnox) toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources