Skip to main content
Glama

Nova Amazon MCP Server

import_tacos_targets

Destructive

Set the TACOS target of products, TWO-STEP like import_vat_categories: call WITHOUT commit first; the server validates each row (an ASIN the workspace's accounts do not sell, or a target that is not a whole percent from 0 to 100, is warned and skipped: never written, and it never blocks the other rows) and returns per-row warnings, the diff (targets set, changed, cleared, unchanged) and a confirmationToken; SHOW them to the user and only after explicit approval call again with the SAME workspace/rows plus commit:true and the token. A TACOS target is the share of a product's sales the seller accepts to spend on ads: a WHOLE percent from 0 to 100 (12 = 12 %, never 0.12; 0 is a real target, 'no ads wanted'), held per child ASIN for the whole organization, every account and marketplace alike. target null CLEARS the product's own target: it follows the organization's default again (set_tacos_default_target). Only the ASINs you send are touched; several rows for one ASIN = the last wins. A committed change is announced to the Nova team, with your reason: say why. Up to 2000 rows per call. One workspace in scope = implicit; several = pass workspace. Requires the OAuth connection and the OWNER role.

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": {
      "rows": "<rows>"
    },
    "name": "import_tacos_targets"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYes
commitNoOmit/false = preview (validate + diff, no write). true = write; requires the confirmationToken from the preview.
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.
workspaceNoWorkspace id or name. Required only when several workspaces are in scope.
confirmationTokenNoThe token the preview returned — proves the user saw exactly this payload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description substantiates exactly what is destroyed: target null CLEARS the product's own target so it reverts to the org default, and only the ASINs sent are touched. It further discloses validation behavior (bad ASINs or non-whole-percent targets are warned, skipped, and never block other rows), last-row-wins on duplicate ASINs, the 2000-row cap, and that a committed change is announced to the Nova team with the supplied reason.

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 critical two-step commit workflow is front-loaded and almost every clause carries necessary information, with no filler. It is a dense run-on though, splicing many separate rules with semicolons and mid-sentence emphasis; breaking the validation rules, the percent semantics, and the auth requirements into discrete statements would make it easier to scan.

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?

No output schema exists, and the description compensates by describing exactly what comes back: per-row warnings, a diff of targets set/changed/cleared/unchanged, and a confirmationToken. Combined with the null-clears semantics and the auth/role requirement, an agent has everything needed to call this correctly on the first attempt.

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 80%, so the schema already carries most per-field meaning and the target description is largely echoed. The description nonetheless adds operational semantics: the 2000-row ceiling, the ambiguity resolution when several rows share an ASIN, and the workspace implicit-vs-explicit rule. `reason` and `confirmationToken` mechanics are explained mostly through the schema itself.

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 ("Set the TACOS target of products") and immediately defines the domain concept: the share of a product's sales the seller accepts to spend on ads. It also distinguishes itself from set_tacos_default_target (which sets the organization default that a null target falls back to) and from import_vat_categories, which it uses as a pattern reference.

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 an explicit two-phase protocol: call without commit first, show the diff and warnings to the user, then call again with commit:true and the token only after explicit approval. It also states prerequisites (OAuth connection, OWNER role) and the scope rule (one workspace implicit, several requires the workspace parameter).

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.