Custom Blinds Shop

request_swatch

Log up to 5 colour codes against an EXISTING order for the team (order_ref required; without it the tool returns status order_required and logs nothing). Sample swatches, not off-cuts: on orders over R8,000 the customer can ask on WhatsApp for swatches in the colours they like, for the product they are ordering; if nothing suits, full refund with no fees. Never quote a sample price or courier cost.

Input Schema

Name	Required	Description
`suburb`	No	Optional delivery suburb
`order_ref`	Yes	The order reference the swatches ship with. Required.
`swatch_codes`	No	Optional specific colour codes (max 5)
`customer_name`	Yes	Customer's full name.
`customer_email`	Yes	Customer's email address.
`customer_phone`	Yes	Used as WhatsApp number
`product_interest`	Yes	e.g. 'Roller Blockout' or 'Honeycomb'

Output Schema

Name	Required	Description	Default
`policy`	No
`status`	Yes
`message`	Yes
`next_step`	No
`order_ref`	No
`request_id`	No
`swatch_count`	No
`estimated_delivery_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 28, 2026
- addedInput schema / properties / customer_email / description
```
Added value: +"Customer's email address."
```
- addedInput schema / properties / customer_name / description
```
Added value: +"Customer's full name."
```

Changed7 schema fields changedOct 20, 2026

addedInput schema / properties / order_ref

Added value: +{
+  "description": "The order reference the swatches ship with. Required.",
+  "type": "string"
+}

changedInput schema / properties / swatch_codes / description

Previous value: -"Optional specific colour codes; no count limit enforced by this handler"New value: +"Optional specific colour codes (max 5)"

changedInput schema / required

Previous value: -[
-  "customer_name",
-  "customer_email",
-  "customer_phone",
-  "product_interest"
-]New value: +[
+  "customer_name",
+  "customer_email",
+  "customer_phone",
+  "product_interest",
+  "order_ref"
+]

addedOutput schema / properties / next_step
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / order_ref
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / policy
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / required

Previous value: -[
-  "request_id",
-  "status",
-  "estimated_delivery_days",
-  "swatch_count",
-  "message"
-]New value: +[
+  "status",
+  "message"
+]

Changed2 schema fields changedOct 11, 2026

changedInput schema / properties / swatch_codes / description

Previous value: -"Optional specific colour codes (max 5)"New value: +"Optional specific colour codes; no count limit enforced by this handler"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "estimated_delivery_days": {
+      "additionalProperties": true,
+      "properties": {
+        "max": {
+          "type": "number"
+        },
+        "min": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "min",
+        "max"
+      ],
+      "type": "object"
+    },
+    "message": {
+      "type": "string"
+    },
+    "request_id": {
+      "type": "number"
+    },
+    "status": {
+      "type": "string"
+    },
+    "swatch_count": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "request_id",
+    "status",
+    "estimated_delivery_days",
+    "swatch_count",
+    "message"
+  ],
+  "type": "object"
+}

First observedMay 25, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations, it discloses the important mutation behavior: it logs colour codes, fails with status order_required when order_ref is missing, logs nothing in that case, and enforces a maximum of 5 codes. It also describes the business policy around eligibility and refunds, which is valuable context for an agent handling the request.

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

Conciseness5/5

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

The core action and failure mode are front-loaded, followed by the sample-vs-off-cut distinction and relevant policy constraints. The description is dense but every sentence carries operational or policy meaning, with no filler.

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?

Given the output schema and full input schema coverage, the description supplies the remaining business context an agent needs: existing-order requirement, missing-order_ref behavior, max swatches, eligibility threshold, sample/off-cut distinction, and pricing prohibitions. Nothing material appears missing for correct invocation.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all parameters, including order_ref being required and swatch_codes having a maximum of 5. The description reinforces the order_ref requirement and links swatches to the product being ordered, but does not add syntax or format details beyond the structured fields.

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?

The description gives a precise verb and resource: logging up to 5 colour codes against an existing order. It also distinguishes the request from off-cuts by clarifying that these are sample swatches, which is useful differentiator language in a catalogue/order toolset.

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?

It clearly states the core precondition: order_ref is required, and without it the tool returns order_required and logs nothing. It also states eligibility (orders over R8,000) and policy exclusions (not off-cuts, never quote sample or courier prices). It does not explicitly name an alternative sibling tool, so it falls short of a 5.

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

All Custom Blinds Shop tools Inspect

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

Need Help?