Skip to main content
Glama
Sign In

Refs

by video.refs
OverviewDiscussionsAdmin

Scan a product's competitors for their winning UGC ads

ugc_scan

Paste a product page and Refs finds the UGC ads (creator-style vertical video ads on Meta and TikTok) that are working for its competitors, then takes them apart. Two steps. (1) ugc_scan(url) reads the page and returns a draft: the product (name, category, price, audience) and 5–8 suggested competitors, each with its site, Facebook Page and TikTok handle. Nothing is queued and no scan is used yet. Show the user the list and let them add, remove or fix competitors (at most 10). (2) ugc_scan(id, competitors?, confirm: true) saves the final list and queues the scan; it uses 1 of the account's 3 scans a month, and a scan that fails gives it back. Only confirm after the user has agreed to the list. Then the Refs worker finds each competitor's ads, ranks them by how long and how hard they ran, keeps the top 25 (at most 5 per competitor), reuses the ones already in the library and measures and blueprints the rest; it usually takes under an hour. Follow it with get_ugc_scan(id). Calling ugc_scan(url) again with a link that's already a draft or being scanned returns that scan. Pro only, free in credits; private to the user.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ugc_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoStep 2: the scan id from step 1 (or its refs.video/ugc/… link), to edit or confirm that draft
urlNoStep 1: the product's page, e.g. https://www.yourbrand.com/products/serum (https; a public site)
confirmNotrue queues the scan (uses 1 of the month's 3). Only once the user has seen and agreed to the competitors
competitorsNoReplaces the draft's list, at most 10. Send the whole final list, including the suggestions the user kept

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
-  "type": "string"
-}
    • removedInput schema / properties / llm_model
      Removed value: -{
-  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
-  "type": "string"
-}
    • removedInput schema / required
      Removed value: -[
-  "context",
-  "llm_model"
-]
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (which only say non-read-only, open-world, non-idempotent), the description discloses that step 1 queues nothing, step 2 consumes 1 of 3 monthly scans with a refund on failure, the job usually finishes under an hour, the plan is Pro-only and results are private. It also notes that re-calling with an existing draft/scan URL returns that scan, a behavior the schema does not 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?

It is long but front-loaded and numbered as 'Two steps', so an agent can scan it quickly. A few phrases ('then takes them apart', the trailing Pro/free/private remarks) could be tightened, but nearly every sentence carries operational information.

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?

There is no output schema, so the description carries the return-value burden itself: it describes the draft shape (product fields plus competitors with site, Facebook Page and TikTok handle) and where to get the final results. For a multi-step, stateful, cost-bearing tool, the definition gives an agent 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.

Parameters4/5

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

Schema coverage is 100%, so per-parameter meaning is already documented; the description still adds cross-parameter semantics the schema cannot: url selects step 1, id selects step 2, confirm triggers the charge, and competitors replaces the whole list (max 10) including kept suggestions. Slightly less explicit on the url/id mutual exclusivity, but otherwise strong.

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 states a concrete verb and resource: it reads a product page, extracts the product and 5–8 competitor suggestions, then queues a scan of competitors' UGC ads. It explicitly distinguishes its own two modes and points to get_ugc_scan as the follow-up tool, so an agent can separate it from every listed sibling.

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?

It spells out the flow: call ugc_scan(url) first, show the list, let the user edit, and only then call ugc_scan(id, competitors, confirm: true). It states the 'when-not' condition ('Only confirm after the user has agreed to the list') and names the follow-up tool, leaving nothing to inference.

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

All Refs 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