Skip to main content
Glama

ads_create_sp_campaign

Create a SP campaign. campaign.targeting_type: "AUTO" (Amazon sceglie automaticamente i target — NON aggiungere keyword/target manuali; per modulare i bid dei 4 gruppi auto usa ads_create_sp_product_targets con auto_match) oppure "MANUAL" (default; poi attacchi keyword via ads_create_sp_keywords o ASIN via ads_create_sp_product_targets). Placement bidding: passa placement_bidding [{placement, percentage}] con placement PLACEMENT_TOP|PLACEMENT_PRODUCT_PAGE|PLACEMENT_REST_OF_SEARCH|SITE_AMAZON_BUSINESS (0-900%). Strategy via dynamic_bidding.strategy (LEGACY_FOR_SALES|AUTO_FOR_SALES|MANUAL|RULE_BASED). Optionally assign to a portfolio via portfolio_id.

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": {
      "campaign": "<campaign>"
    },
    "name": "ads_create_sp_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
campaignYesCampagna da creare: oggetto con name, targetingType, state, budget, startDate… (formato Amazon Ads v3).
account_idNoID dell'outpost Amazon (= un seller su uno specifico marketplace; vedi list_clients). Opzionale se il token è legato a un solo outpost.
confirm_idNoToken di conferma ritornato dall'anteprima. Ripassa lo STESSO payload + confirm_id per eseguire davvero la scrittura.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • addedInput schema / properties / campaign / description
      Added value: +"Campagna da creare: oggetto con name, targetingType, state, budget, startDate… (formato Amazon Ads v3)."
    • addedInput schema / properties / campaign / properties / daily_budget / description
      Added value: +"Budget giornaliero in valuta del marketplace, es. 15."
    • addedInput schema / properties / campaign / properties / dynamic_bidding / description
      Added value: +"Strategia di bidding dinamico, es. { \"strategy\": \"LEGACY_FOR_SALES\" }."
    • addedInput schema / properties / campaign / properties / end_date / description
      Added value: +"Data di fine, formato YYYY-MM-DD, es. 2026-11-30."
    • addedInput schema / properties / campaign / properties / name / description
      Added value: +"Nome della campagna/portfolio/ad group, visibile in console Amazon Ads."
    • addedInput schema / properties / campaign / properties / placement_bidding / description
      Added value: +"Modifiche bid per posizionamento: array di { placement, percentage }."
    • addedInput schema / properties / campaign / properties / placement_bidding / items / properties / percentage / description
      Added value: +"Variazione percentuale del bid come intero, es. 50 = +50%."
    • addedInput schema / properties / campaign / properties / placement_bidding / items / properties / placement / description
      Added value: +"Posizionamento: PLACEMENT_TOP (primo risultato), PLACEMENT_REST_OF_SEARCH, PLACEMENT_PRODUCT_PAGE."
    • addedInput schema / properties / campaign / properties / portfolio_id / description
      Added value: +"Id portfolio Amazon Ads (da ads_list_portfolios)."
    • addedInput schema / properties / campaign / properties / profile_id / description
      Added value: +"Amazon Ads profile id (stringa numerica, da ads_list_profiles). Omesso: profilo predefinito dell'outpost."
    • addedInput schema / properties / campaign / properties / start_date / description
      Added value: +"Data di inizio, formato YYYY-MM-DD, es. 2026-11-10."
    • addedInput schema / properties / campaign / properties / state / description
      Added value: +"Stato: ENABLED, PAUSED oppure ARCHIVED (maiuscolo; ARCHIVED è irreversibile)."
    • addedInput schema / properties / campaign / properties / targeting_type / description
      Added value: +"MANUAL o AUTO."
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true; the description goes beyond them by explaining the downstream behavioral consequence of targeting_type=AUTO versus MANUAL and by enumerating bidding strategies and placement bid ranges. It does not itself surface the preview/confirm two-step write flow, though that is documented in the confirm_id parameter.

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 purpose sentence is front-loaded and the mode/bidding details follow in a logical order, so nothing is buried. It is dense and parenthetical, with mixed Italian/English and long nested clauses, which slightly raises reading cost for an agent.

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 nested-object creation tool with no output schema, the description covers the decision-critical configuration paths (targeting type, placements, strategy, portfolio) and the follow-up tools. Remaining gaps — required name/budget fields and the preview-then-confirm write pattern — are already carried by the schema.

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 baseline is 3; the description adds real meaning by spelling out the dynamic_bidding.strategy values (LEGACY_FOR_SALES|AUTO_FOR_SALES|MANUAL|RULE_BASED) and the placement percentages (0-900%), and even lists SITE_AMAZON_BUSINESS, which the schema's own placement description omits. It does not clarify budget/date/portfolio defaults beyond what the schema states.

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?

"Create a SP campaign" states a specific verb and resource, and the description immediately branches into the two creation modes (AUTO vs MANUAL) that an agent must choose between. Follow-up siblings (ads_create_sp_keywords, ads_create_sp_product_targets) are named, so the agent can distinguish creation from later configuration.

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 concrete guidance on which mode to pick and what NOT to do (AUTO forbids manual keywords/targets; MANUAL defaults and then requires keyword/ASIN attachment via the named sibling tools). It lacks an explicit exclusion against updating an existing campaign (ads_update_sp_campaign) or prerequisites such as profile/portfolio setup, so it stops short of full when/when-not coverage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources