Go Shift

Create a Snapchat catalog campaign

snapchat_create_catalog_campaign

Build a Snapchat catalog (dynamic product) campaign in ONE call: a Sales campaign linked to a catalog, an ad squad on a product set, a dynamic creative and its ad. Everything is created PAUSED. audience chooses who it reaches: prospecting (new people), retarget_viewers (viewed or added to cart, did not buy) or retarget_cart (added to cart, did not buy). Needs a Snap Pixel on the account and a catalog with a product set (see snapchat_catalogs). The dynamic template lays out the product: the account's template is used, and when the account has none a basic one (product image with title and price) is created with the campaign. Always offer dry_run=true first and show the plan; launching is snapchat_set_status with include_children=true after the user's yes.

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": {
      "name": "<name>",
      "catalog": "<catalog>",
      "audience": "<audience>",
      "countries": "<countries>",
      "daily_budget": "<daily_budget>",
      "headline": "<headline>"
    },
    "name": "snapchat_create_catalog_campaign"
  }
}

Input Schema

Name	Required	Description
`bid`	No	Needed unless AUTO_BID (account currency).
`name`	Yes
`folder`	No	Client folder name.
`account`	No	Snapchat ad account name or ID. Optional when only one is enabled.
`catalog`	Yes	Catalog name or ID.
`dry_run`	No
`audience`	Yes	Who to reach. Ask the user; don't pick silently.
`end_time`	No	ISO date-time.
`headline`	Yes
`language`	No	Language of the card: the language the user is writing in.
`pixel_id`	No	Default: the account's active Pixel.
`countries`	Yes	ISO country codes, e.g. ["sa"].
`brand_name`	No
`profile_id`	No
`bid_strategy`	No	Default AUTO_BID.
`daily_budget`	Yes	Ad squad daily budget in the account currency.
`call_to_action`	No	Default SHOP_NOW.
`product_set_id`	No	Product set to advertise. Default: the catalog's default set (all products).
`retention_days`	No	How far back product views, carts and purchases count. Default 14.
`template_layout`	No	Layout of the template created when the account has none. Default AUTOMATIC.
`optimization_goal`	No	Default PIXEL_PURCHASE.
`dynamic_template_id`	No	Dynamic template that lays out the product. Default: the ad account's only template; if it has none, a basic one is created.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only say this is a non-readOnly, non-destructive, open-world write; the description adds the crucial behavioral facts: everything is created PAUSED, a Snap Pixel on the account is required, and a basic dynamic template is auto-created when the account has none. It also explains default resolution for the template and the audience semantics beyond the enum names.

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?

Dense and front-loaded, with the created-objects list first, then the behavioral constraints, then the dry_run/launch workflow. The audience sentence is long and packed with parentheticals, making it read as a run-on, but every sentence carries information an agent needs.

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 22-parameter, multi-object creation tool with no output schema, this covers prerequisites, pause state, template fallback, audience definitions, and the follow-up launch step. It does not say what the call returns (e.g., IDs of the campaign/squad/creative) or how partial failures are handled, which would matter for a one-call multi-entity create.

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 77%, so the schema already carries most parameter meaning. The description still adds value by spelling out what each audience enum value actually means ('prospecting (new people)', 'retarget_viewers (viewed or added to cart, did not buy)', 'retarget_cart'), which the enum list alone does not convey, and by explaining the template fallback used for dynamic_template_id.

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 specific verb and resource ('Build a Snapchat catalog (dynamic product) campaign in ONE call') and enumerates exactly what gets created: a Sales campaign linked to a catalog, an ad squad on a product set, a dynamic creative and its ad. This distinguishes it from snapchat_create_campaign (non-catalog) and from the individual snapchat_create_ad / snapchat_create_adsquad / snapchat_create_creative atomic tools.

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?

Gives explicit workflow guidance: always offer dry_run=true first and show the plan, then launch with snapchat_set_status using include_children=true after user confirmation. Also names prerequisites and points to the sibling snapchat_catalogs for catalog/product set setup, so the agent knows what to do before and after this call.

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

All Go Shift 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?