AMZ Vault

Stage: Add negatives

stage_negatives

Propose adding negative keywords / negative ASIN targets. Items: campaign_id + keyword_text (SP/SB) or asin_target (SP/SD) or brand_id (SD). Levels: SP campaign or ad_group (pass ad_group_id); SB and SD are AD-GROUP level — ad_group_id required (SB is keyword-only, SD is product/brand-only). match_type: NEGATIVE_EXACT (default) | NEGATIVE_PHRASE | NEGATIVE_BROAD — any casing (negativeExact, exact) is accepted and normalized to the correct per-API wire form; SB has no broad. STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.

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": {
      "items": "<items>"
    },
    "name": "stage_negatives"
  }
}

Input Schema

Name	Required	Description
`items`	Yes
`reason`	No	Why THIS change, 1-3 sentences specific to it - shown in the approval modal
`profile_id`	No	Which advertising profile (see account_profiles). Optional when the token has exactly one.
`candidate_action_id`	No	The candidate action (Strategist Layer, What to do list) this change executes; one proposal per action id

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026

addedInput schema / properties / candidate_action_id

Added value: +{
+  "description": "The candidate action (Strategist Layer, What to do list) this change executes; one proposal per action id",
+  "type": "integer"
+}

First observedSep 5, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The description goes well beyond annotations by explaining that this only saves a reviewable diff in AMZ Vault and does not modify Amazon until confirmation. It also discloses normalization behavior and platform constraints such as SB lacking broad match, which are important behavioral traits.

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?

The description is dense but well organized and front-loaded with purpose, then item structure, level rules, match_type normalization, and staging behavior. Every sentence carries actionable information for correct invocation.

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

Completeness5/5

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

Given the staging workflow, platform-specific item formats, and absence of an output schema, the description is complete enough to call the tool correctly. It covers how items are shaped, what levels apply, match_type normalization, and the confirmation dependency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 75% description coverage, but the critical items parameter is a generic object array with no nested schema. The description compensates by defining item shapes: campaign_id plus keyword_text, asin_target, or brand_id, along with required level and match_type rules.

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 states a specific verb and resource: 'Propose adding negative keywords / negative ASIN targets.' It clearly distinguishes this add/stage operation from the sibling remove operation by focusing on additions, and the title reinforces 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?

The staging-only workflow is explicit: nothing is sent to Amazon until confirm_staged_changes is called. It also gives platform-specific item requirements and match_type behavior, but it does not explicitly name when to choose this over ppc_negation_candidates or stage_negatives_remove.

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

All AMZ Vault 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?