Skip to main content
Glama
Sign In

Emberfeed

by com.emberfeed
OverviewDiscussionsAdmin

Copy a template to a Meta 4:5 or 9:16 aspect-ratio variant

create_template_variant

Copies an existing template (code OR visual) to a Meta aspect-ratio variant: placement "4_5" (Feed, 1080×1350) or "9_16" (Stories and Reels, 1080×1920). Meta feeds then carry, next to image_link, a tagged image per product that Meta picks for that placement, instead of putting the square image in a taller tile with bars. The copy is INACTIVE: adapt it (update_code_template for code; the web editor for visual), check it with preview_render, then update_code_template {isActive:true} — for visual templates the user activates it in the web UI. Code CSS written with fixed pixel heights needs reworking for the taller canvas; width/height 100% flex layouts carry over. The response repeats the placement's safe zones.

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": {
      "templateId": "<templateId>",
      "placement": "<placement>"
    },
    "name": "create_template_variant"
  }
}

Input Schema

NameRequiredDescriptionDefault
placementYes
templateIdYesThe template to copy, usually the feed's active main template.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, and the description adds substantial context beyond that: the created copy is INACTIVE, activation differs for code vs visual templates (web UI for visual), and code CSS with fixed pixel heights must be reworked. This is exactly the kind of behavioral disclosure that matters before invoking a mutation.

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?

The description is front-loaded with purpose and placement values, then layers the rationale and the required follow-up workflow. It is dense but every sentence carries actionable information; the CSS pixel-height note is slightly tangential but still useful context.

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?

For a two-parameter mutation tool with no output schema, the definition covers what is created (an inactive copy), how to activate it, the different activation paths for code vs visual, and even that the response repeats the placement's safe zones. Nothing critical an agent needs to call and follow through correctly is missing.

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 only 50% schema coverage, the description compensates by explaining both placement values with their platform meaning and dimensions (4_5 = Feed, 1080×1350; 9_16 = Stories and Reels, 1080×1920), and clarifies templateId can be code OR visual. The enum itself is in the schema, but the added semantic mapping and pixel dimensions go beyond it.

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 opens with a specific verb and resource ('Copies an existing template') and immediately scopes it to a Meta aspect-ratio variant with the two exact placement values and their pixel dimensions. This clearly distinguishes it from siblings like create_code_template and create_feed, so an agent can identify it without opening the schema.

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 explains the motivating scenario (avoiding square images letterboxed into taller tiles) and gives a full post-copy workflow: adapt via update_code_template or the web editor, check with preview_render, then activate. It names the relevant sibling tools as next steps but does not explicitly state when NOT to use this tool (e.g., when no base template exists yet).

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

All Emberfeed 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