Skip to main content
Glama
Ads MCP for Snapchat

Ads MCP for Snapchat

by Usame794

snap_blended_roas

Read-only

Compares Snapchat-reported and store-confirmed revenue to flag over- or understatement, shows both ROAS figures, and can add store cost per order.

Instructions

Compare Snap's reported revenue with the revenue your store confirms (read-only). Give store_revenue: what your store credits to Snapchat (for example Shopify or Google Analytics with utm_source=snapchat) for the same days and currency. Window: the last days full local days, or start_date and end_date (YYYY-MM-DD, both included, up to 31 days). Says whether Snap overstates, understates or is consistent, with both ROAS figures. Optional store_orders adds the store's cost per order.

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": {
      "store_revenue": "<store_revenue>"
    },
    "name": "snap_blended_roas"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
end_dateNo
start_dateNo
store_ordersNo
store_revenueYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the 'read-only' note is partly redundant, but the description adds real behavior: the exact output semantics (overstates/understates/consistent plus both ROAS values) and the window rules including the 31-day cap and inclusive dates. It stops short of saying what happens when the two datasets don't align (mismatched currency or missing days).

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 front-loaded with the comparison purpose, then inputs, then window rules, then output, in a logical order with almost no filler. A couple of clauses ('Give store_revenue: what your store credits to Snapchat') are slightly awkward but still earn their place.

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

Completeness4/5

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

For a 5-parameter read tool with no output schema, the description covers what is needed to call it and what comes back (a consistency verdict plus two ROAS figures). The remaining hole is edge behavior: currency mismatch, partial data, and the days-vs-date-range interaction, which an agent would have to guess.

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 description coverage is 0%, so the description carries the load and largely does: store_revenue is defined by source and scope, and the days vs start_date/end_date window is explained with format (YYYY-MM-DD), inclusivity, and the 31-day limit. The gap is store_orders, described as adding 'the store's cost per order' for an integer parameter whose name suggests an order count, plus no statement on whether days and explicit dates are mutually exclusive.

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 names a precise verb and resource: it compares Snap's reported revenue against store-confirmed revenue and reports over/under-statement plus both ROAS figures. That is specific enough that an agent can tell this is a reconciliation tool, not an ads-management or reporting tool, and no sibling in the catalog overlaps with it.

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 gives clear pre-call guidance: you must supply store_revenue representing what the store credits to Snapchat (Shopify or GA with utm_source=snapchat) for the same days and currency, and optionally store_orders. What is missing is explicit when-not-to-use guidance or a named alternative when the store data isn't available in the same currency or window.

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

Deploy Server

Other Tools