Skip to main content
Glama
Ads MCP for Snapchat

Ads MCP for Snapchat

by Usame794

snap_influencer_ad

Claim a creator ad code, build its web-view creative, and create a paused ad in an ad squad using a preview-then-confirm workflow.

Instructions

Full influencer flow in one step: claim a creator ad code, wait for the media, create a WEB_VIEW creative, and create a PAUSED ad in the given ad squad. Claiming is one-way (single-use code). Previews (nothing sent) unless confirm=true. Two steps: confirm=false returns a preview and an approval_token; to apply, repeat the same arguments with confirm=true and that approval_token.

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": {
      "ad_code": "<ad_code>",
      "adsquad_id": "<adsquad_id>",
      "name": "<name>",
      "headline": "<headline>",
      "url": "<url>"
    },
    "name": "snap_influencer_ad"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
nameYesUsed for the creative and the ad, e.g. 'Paid - handle - SKU'
ad_codeYes
confirmNofalse = preview only (nothing sent). true = apply; needs approval_token from the preview.
headlineYes
adsquad_idYes
profile_idNo
approval_tokenNoThe approval_token returned by the preview of this exact request. Required with confirm=true.
call_to_actionNoSHOP_NOW

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the description carries the real burden and does it well. It discloses that claiming a code is one-way and single-use, that the resulting ad is created PAUSED (a meaningful safety property), and that preview mode sends nothing. These are exactly the side-effect facts an agent cannot get from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, all load-bearing: the flow is front-loaded first, then the irreversible claim caveat, then the preview safety note, then the two-step procedure. No filler and no restatement of the title or schema.

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 9-parameter mutating orchestration tool with no output schema and no annotations covering side effects, the description gives the agent enough to call it safely and correctly. The gap is the return shape after confirm=true: it says preview returns an approval_token but not what apply returns (ad id, creative id, or media-wait failure behavior).

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 only 33% across 9 parameters, but the description compensates on the highest-risk ones: confirm and approval_token get their exact lifecycle and coupling explained, ad_code gets its single-use semantics, adsquad_id gets its role, and name gets its formatting purpose. url, headline, profile_id, and call_to_action are left to their names, with profile_id being the one genuinely ambiguous parameter still unexplained.

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?

Names a specific composite action and enumerates every sub-step: claim the ad code, wait for media, create a WEB_VIEW creative, create a PAUSED ad in the given ad squad. The phrase 'Full influencer flow in one step' implicitly distinguishes it from the granular siblings (snap_claim_ad_code, snap_create_ad) without needing to name them.

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?

Explicitly describes the two-call protocol: call with confirm=false to get a preview plus approval_token, then repeat identical arguments with confirm=true and that token. It states the condition that selects each mode and warns that nothing is sent during preview. It does not say when an agent should prefer the granular claim/create siblings over this bundled flow, which is the only missing routing guidance.

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