Skip to main content
Glama

Nova Amazon MCP Server

get_tacos_worksheet

Read-only

The TACOS targets worksheet of ONE workspace, the dashboard's bulk file as JSON: a row per child ASIN the workspace's accounts sell (sold in the last 24 months, or holding a target) with its name, parent ASIN, marketplaces, its last 30 days as the cockpit reads them, currentTarget (the target it is held against) and ownTarget (null = it follows the default). The L30D figures of a row come from one read of the cockpit's engine over period (the 30 days up to yesterday, both included), on the Seller Central accounts, with the organization's saved P&L rules: unitsL30D, salesL30D and adSpendL30D (the cockpit's Units, Sales and PPC Spend, the amounts in currency, the organization's), tacosL30D (adSpendL30D over salesL30D in percent, the PPC TACOS the Live page holds against the target; null without sales), marginBeforeAdsL30D and netMarginL30D (percent; on net sales when the organization's P&L policy says so). A null figure means the cockpit holds none for the product over those days (nothing sold nor spent), never 0. 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 %; 0 = no ads wanted), set per child ASIN for the whole ORGANIZATION, every account and marketplace alike. defaultTarget is the organization's default, what every product without its own target is held against (12 until the organization sets one: isDefaultSet false). A group (a parent ASIN, a marketplace, an account) stores no target: the Live page reads its products' targets weighted by their sales. Use it to match a seller's list to exact ASINs before building import_tacos_targets rows. One workspace in scope = implicit; several = pass workspace. Server-side pagination: limit/offset, total returned.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_tacos_worksheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
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 (from list_accounts). Required only when several workspaces are in scope.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover the read-only, closed-world safety profile, and the description adds substantial context on top: figures come from a single engine read over the 30 days up to yesterday, amounts use the organization's currency and saved P&L rules, and null explicitly means 'no data held', never 0. It also discloses that targets are per child ASIN for the whole organization and that groups store no target (weighted by sales), plus that pagination is server-side.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core payload is front-loaded in the first sentence, but the body is a dense run of long parenthetical sentences mixing return-field definitions, target-domain background, and grouping semantics. Little is pure filler given the absence of an output schema, yet the prose could be restructured into scannable clauses without losing content.

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?

With no output schema and only 50% schema coverage, the description carries the full burden and does: it defines every returned field (unitsL30D, salesL30D, adSpendL30D, tacosL30D, margin fields, currentTarget, ownTarget, defaultTarget, isDefaultSet), the null convention, and the pagination and scoping behavior. An agent can call and interpret the result without further documentation.

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 50% — `reason` and `workspace` are documented in the schema, while `limit` and `offset` carry only bounds. The description compensates for the workspace parameter's conditional requirement and flags that limit/offset drive server-side pagination with a total returned, but it never states default page size or the ordering of results.

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 opening sentence names the exact resource (the TACOS targets worksheet), its scope (ONE workspace, dashboard bulk file as JSON) and the row grain (a row per child ASIN sold in the last 24 months or holding a target). It also explicitly separates itself from import_tacos_targets by framing itself as the read step before building import rows.

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 a concrete use case (match a seller's list to exact ASINs before building import_tacos_targets rows) and resolves the workspace-parameter condition (implicit for one workspace, pass `workspace` when several are in scope). It does not state when NOT to use it or contrast with the other get_*_worksheet siblings, so it falls short of full when/when-not guidance.

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.