Skip to main content
Glama

Start a window or patio preview

start_visualiser_preview

Show the customer a blind on THEIR OWN window or patio, in this chat. Pass the photo they gave you (image_url https, or image_base64; for outdoor blinds, the patio opening taken straight on), the product_id and an exact in-stock colour name (get_product), and the customer's name and South African WhatsApp number (required: the team follows up on WhatsApp, and each number gets 2 free previews). Indoor blinds, and the outdoor screen, clear PVC and canvas blinds (not outdoor bamboo). Finds the windows or patio openings (20 to 45 s) and returns job_id; then call get_visualiser_preview. A preview of colour and style, not a measuring tool.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "product_id": "<product_id>",
      "colour": "<colour>",
      "customer_name": "<customer_name>",
      "whatsapp": "<whatsapp>"
    },
    "name": "start_visualiser_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
colourYesExact in-stock colour name from get_product (for a Duo Roller, one of its listed colours)
whatsappYesCustomer's South African WhatsApp number
image_urlNohttps URL of the customer's window or patio photo (JPEG, PNG or WebP, under 6 MB)
product_idYesVisualiser blind, e.g. roller-blockout, duo-roller, venetian-25mm-aluminium, honeycomb-blockout, outdoor-blinds, outdoor-blinds-pvc, outdoor-blinds-canvas
image_base64NoOr the photo itself, base64
customer_nameYes

Output Schema

NameRequiredDescriptionDefault
noteNo
colourYes
job_idYes
statusYes
next_stepYes
product_idYes
windows_foundYes
remaining_previewsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safety profile (mutating relative to readOnlyHint=false, openWorldHint=true, non-destructive), and the description adds the operational detail that matters: processing takes 20-45 s, a job_id comes back, the team follows up on WhatsApp, and the output is a style/colour preview, not a measurement. That is well beyond what structured fields convey.

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?

One dense, front-loaded block that leads with what the tool does before the prerequisites and category carve-outs. The long parenthetical chains (base64, patio angle, product exclusions) make it heavier than ideal, but no sentence is 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 an output schema, the description needn't document the return payload, yet it still tells the agent that job_id comes back and that get_visualiser_preview is the next call. Prerequisites, exclusions, latency expectation and real-world side effects (WhatsApp follow-up) are all covered for a 6-parameter tool.

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

Parameters4/5

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

With 83% schema coverage the baseline is 3, and the description earns above that by tightening the contract: colour must be an exact in-stock name obtained from get_product, the WhatsApp number must be South African, and for outdoor blinds the patio shot must be taken straight on. The image_url vs image_base64 choice is echoed rather than expanded beyond the schema.

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?

States a concrete verb+resource+scope: "Show the customer a blind on THEIR OWN window or patio, in this chat" — the emphasis on their own window and in-chat delivery distinguishes it from the visualiser-URL sibling. An agent can tell it starts a preview job rather than retrieving one.

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

Usage Guidelines5/5

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

Explicitly scopes the eligible products (indoor blinds plus outdoor screen, clear PVC and canvas blinds, excluding outdoor bamboo) and prescribes the follow-up step (call get_visualiser_preview after job_id). It also names a hard constraint — a South African WhatsApp number is required and gets 2 free previews per number.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources