Gloriads — Amazon Ads

Performance totals

get_summary

Read-onlyIdempotent

Get the Amazon Ads totals of a period, the same figures as the dashboard: spend, sales, ACOS (in %), ROAS, impressions, clicks, CTR, average CPC, purchases and conversion rate, plus the same per marketplace and per ad type (with each type's share of spend). With compare, the compared period's figures and each change too, in one call. Answers "how did my ads do last month?", "which marketplace spends the most?" or "is my ACOS better than the month before?". Streaming TV is not included (see get_streaming_tv_report). Amounts are in USD (Amazon converts each marketplace). meta.data_last_date says up to which day the figures go.

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_summary"
  }
}

Input Schema

Name	Required	Description
`range`	No	Relative period, resolved in `timezone`, e.g. "last_30_days", "this_month", "last_year", or "all_time" (from the oldest data held, through today). Ranges cover complete days like the dashboard: "last_30_days" is the 30 days ending yesterday, "this_month" stops at yesterday, "today" is today. Defaults to "last_30_days". Do not combine with start_date/end_date.
`compare`	No	"previous_period" (the same number of days just before; "this_month" against the same days of last month) or "same_period_last_year" (the same dates a year earlier). Adds the compared period's figures and how each changed (the dashboard's "+18 %"). Both periods then end yesterday. Absent: no comparison.
`end_date`	No	Last day, inclusive (YYYY-MM-DD). A date after today is treated as today.
`timezone`	No	IANA time zone deciding which day "today" is for `range`, e.g. "Europe/Paris". Defaults to UTC.
`start_date`	No	First day, inclusive (YYYY-MM-DD). Send together with end_date.
`ad_products`	No	Keep only these ad types: SPONSORED_BRANDS, SPONSORED_DISPLAY, SPONSORED_PRODUCTS. Absent: all of them.
`marketplaces`	No	Keep 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.

First observedNov 3, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is largely covered. The description adds genuinely useful behavior beyond that: amounts are USD-converted, all ranges end yesterday like the dashboard, comparison periods end yesterday too, and meta.data_last_date exposes data freshness. It stops short of describing response shape or how sparse markets are handled, so a 3 fits against an already-declared annotation set.

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 the primary purpose and the metric list, then breakdowns, then comparison behavior, then the exclusion and currency/freshness caveats. The metric enumeration is long but each item is informative; no filler sentences, though the density pushes the limit of a single paragraph.

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, so the description carries the full burden of describing return content — and it does: the named metrics, per-marketplace and per-ad-type breakdowns with spend share, comparison deltas, currency, and the freshness field. An agent knows exactly what shape of answer to expect and when the data ends.

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

Parameters3/5

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

Schema description coverage is 100%, so the enum values, defaults and date-pairing rules are already documented in structured fields. The description adds only modest meaning on top (comparison figures arrive 'in one call', currencies normalized to USD, both periods end yesterday), so the baseline 3 is the right level.

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?

Specific verb and resource ('Get the Amazon Ads totals of a period') plus an explicit enumeration of returned metrics (spend, sales, ACOS, ROAS, impressions, clicks, CTR, CPC, purchases, conversion rate) and their breakdowns. It also names the one sibling it is not (get_streaming_tv_report), so an agent can separate it from the report tools without opening a schema.

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 example questions that map to the tool ('how did my ads do last month?', 'which marketplace spends the most?') and states the exclusion with a pointer to get_streaming_tv_report. It does not contrast with get_timeline or get_products_report, so the routing for trend or product-level questions is left implicit.

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

All Gloriads — Amazon Ads 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?