Skip to main content
Glama
Amazon Ads MCP Server

Amazon Ads MCP Server

by get-mcp-ads

amazon ads get negative keywords

amazon_ads_get_negative_keywords
Read-onlyIdempotent

Retrieves one page of Amazon Sponsored Products negative keywords, including paused and archived entries by default, for a specified advertising profile; use nextToken to continue.

Instructions

Read one page of Amazon Sponsored Products negative keywords, including paused and archived entities by default. Continue with nextToken until absent; one page is not an account total. These are configuration records, not performance metrics.

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": {
      "accountId": "<accountId>"
    },
    "name": "amazon_ads_get_negative_keywords"
  }
}

Input Schema

NameRequiredDescriptionDefault
statesNoDelivery states to include. Defaults to every state, archived included.
accountIdYesAdvertising profile ID listed in AMAZON_ADS_PROFILE_IDS, such as 1234567890. The region-qualified form used by hosted getmcpads, such as EU:1234567890, is accepted when its region matches AMAZON_ADS_REGION.
nextTokenNoOpaque continuation token from the previous page for this same profile and filters. Omit on the first request.
maxResultsNoMaximum entities in this page, up to 100. Follow the returned continuation value for the rest.
campaignIdsNoRestrict results to these campaign IDs, as decimal strings.

Output Schema

NameRequiredDescriptionDefault
resultYesOriginal tool result: parsed JSON when the text is JSON, otherwise the text or multiple MCP content blocks. Provider fields depend on the selected query.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.1
    • changedOutput schema / properties / result / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "properties": {},
      -    "type": "object"
      -  },
      -  {
      -    "items": {},
      -    "type": "array"
      -  },
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {},
      +    "type": "object"
      +  },
      +  {
      +    "items": {},
      +    "type": "array"
      +  },
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real operational context: default inclusion of paused/archived states and the warning that a single page is not a complete account total, which prevents a common aggregation mistake. It does not mention throttling or result-size cost, so it stops short of 5.

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?

Three tight sentences: scope first, pagination obligation second, data-type disambiguation last. Nothing is repeated verbatim from the schema and every sentence carries decision-relevant information.

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?

With an output schema present, return values needn't be explained, and pagination plus default state coverage are handled well. The remaining gap is scope disambiguation against the campaign-level negative keyword sibling, which the agent would have to infer.

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 the baseline is 3. The description still adds value by tying nextToken and page size together semantically ('one page is not an account total'), clarifying what maxResults actually bounds beyond the schema's 'Maximum entities in this page'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('Read one page of Amazon Sponsored Products negative keywords'), and the 'Sponsored Products' qualifier separates it from the SB/SD siblings (amazon_ads_get_sb_negative_keywords, amazon_ads_get_sd_negative_targets). It does not, however, clarify its relationship to amazon_ads_get_campaign_negative_keywords, so the level (campaign vs ad group) this returns is left ambiguous.

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?

Gives a concrete pagination procedure ('Continue with nextToken until absent; one page is not an account total'), which is the main usage trap for this tool. The closing exclusion 'configuration records, not performance metrics' steers agents away from using it for performance analysis, but no sibling is named explicitly as the alternative.

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