Skip to main content
Glama

Nova Amazon MCP Server

create_events

Log one or several EVENTS on Nova — dated notes drawn on the charts so a later movement can be explained ("changed the A+ of B0…", "price +10% on amazon.es", "new PPC campaign", "launch"). The seller tells you what they did; log each change with the day it happened. One event covers MANY ASINs and marketplaces when it is the same change (one A+ rework on five ASINs = one event); distinct changes (different day, type or description) are separate entries of events, logged in ONE call. TWO-STEP: call WITHOUT commit; the server resolves each event's account, marketplaces and ASINs against the catalog (child or parent, product name, listed where — a mistyped ASIN shows here) and returns ONE preview with a confirmationToken; show it to the user and only after their approval call again with commitPayload plus commit:true and the token. type is the dashboard's vocabulary: content_change for title/bullets/images/video/A+, price_change for price/deals/coupons, ppc_change for campaigns/bids/budgets, product_launch, other. Check list_events first when the seller may already have logged it. Requires the OAuth connection (a workspace API token cannot write).

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": {
      "events": "<events>"
    },
    "name": "create_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
commitNoOmit/false = preview (resolution + catalog check, no write). true = write; requires the confirmationToken from the preview.
eventsYesOne entry per distinct change. A single event is a one-entry array.
reasonNoOne sentence, ALWAYS IN ENGLISH (regardless of the conversation language), on WHY you are making this call — the user question or your analytical goal. Recorded so the seller can see how their data is used.
confirmationTokenNoThe token the preview returned — proves the user saw exactly these events.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say it is a non-destructive write; the description goes well beyond that by disclosing that a call without `commit` performs no write but instead resolves accounts, marketplaces and ASINs against the catalog and returns a preview with a confirmationToken. It also discloses the auth constraint (OAuth connection required, workspace API token cannot write) and that mistyped ASINs surface during resolution.

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?

Front-loaded with purpose, then aggregation rules, then the two-step procedure, then vocabulary and auth — a sensible order with no filler sentences. It is dense and caps-heavy, and the type vocabulary is restated from the schema, which costs a little tightness.

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?

For a write tool with no output schema, the description covers everything an agent needs: preview/commit semantics, token handling, resolution behavior, auth requirement, consolidation rules, and the enum vocabulary. Nothing material is left for the agent 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 schema already documents every parameter including the commit/preview split and the type enum. The description still adds real meaning beyond the schema: the aggregation rule that one event spans many ASINs and marketplaces, and the date semantics warning that 'today' is the user's date, not UTC.

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 ('Log one or several EVENTS on Nova — dated notes drawn on the charts') and immediately grounds it with concrete examples ('changed the A+ of B0…', 'price +10% on amazon.es'). It is clearly distinguished from the read-side sibling list_events, which is named explicitly.

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 consolidation rules (one A+ rework on five ASINs = one event; distinct day/type/description = separate entries in ONE call) and an explicit exclusion ('Check list_events first when the seller may already have logged it'). It also spells out the two-step preview-then-commit procedure and the auth prerequisite, so the agent knows exactly when and how to invoke it.

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.