Skip to main content
Glama

Gloriads — Amazon Ads

Impression share by search or campaign

get_impression_share
Read-onlyIdempotent

Get the account's share of the ad impressions. level "searches" (default): each search's impression share (in %) and the advertiser's rank among every advertiser on it (1 = the most impressions), per marketplace and ad type, with is_brand_search (the search holds a term of the advertiser's "never negate" keyword list, its brand). level "campaigns": each campaign's top-of-search impression share (join campaign_id with list_campaigns for names). Amazon gives a share over a whole window, never per day: window is one of last_30_days, previous_30_days, last_90_days, last_365_days, all_time (all ending yesterday; campaigns: last_30_days, previous_30_days). Compare last_30_days with previous_30_days to see a share drop. A search with marketplace null was seen on several marketplaces Amazon does not name: its values are in marketplace_values. Answers "do I own my brand searches?", "who outranks me on my main keyword?" or "which campaigns rarely reach the top of search?". If meta.status is "preparing", Amazon is preparing the window: call again after meta.retry_after_seconds.

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_impression_share"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort field, defaults to "impressions". Campaigns: impressions or impression_share only.
levelNo"searches" (default) or "campaigns".
limitNoItems per page, 1 to 1000. Defaults to 100.
orderNo"desc" (default) or "asc". A row without the value always comes last.
cursorNoThe `next_cursor` of the previous page, to read the next one. Treat it as opaque.
windowNoThe days covered, defaults to "last_30_days".
containsNolevel "searches": keep the searches containing this text.
timezoneNoIANA time zone deciding which day "today" is for `range`, e.g. "Europe/Paris". Defaults to UTC.
brand_onlyNolevel "searches": true keeps the brand searches only.
ad_productsNoKeep only these ad types: SPONSORED_BRANDS, SPONSORED_PRODUCTS. Absent: both.
marketplacesNoKeep only these marketplaces, by country code: US, CA, MX, BR, UK, DE, FR, ES, IT, NL, SE, PL, BE, TR, AE, SA, EG, IN, ZA, JP, AU, SG. Absent: every marketplace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark it read-only and idempotent, and the description adds substantial behavior on top: shares are never per-day, every window ends yesterday, campaigns support only two windows, null marketplace rows roll up into marketplace_values, and meta.status "preparing" requires a retry after meta.retry_after_seconds. That is real information an agent cannot get from the structured fields.

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?

Purpose is front-loaded and the mode descriptions follow in a logical order, with no filler sentences. It is dense and somewhat run-on in the middle, but every clause carries operational detail.

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, the description carries the return-shape burden and does so: impression share in percent, advertiser rank with 1 as most impressions, is_brand_search, per-marketplace breakdown, and marketplace_values. It also covers the async-preparing state, which is the main failure mode for a tool like this.

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 3 is the baseline, but the description adds meaning the schema does not: what level actually returns in each mode, which window values are valid for campaigns specifically, and what a null marketplace implies. It does not restate sort, order, limit, or cursor, which the schema already handles.

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 ("Get the account's share of the ad impressions") and immediately enumerates the two modes, "searches" and "campaigns", with what each returns. This separates it cleanly from the sibling report/list tools, which return other metrics.

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 concrete usage contexts via the three example questions and an explicit comparison recipe ("Compare last_30_days with previous_30_days to see a share drop"). It also routes to list_campaigns for campaign names. It does not name a competing tool to avoid, so it stops short of full 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.

Resources