Skip to main content
Glama

Get Ad Spend Trend

get_ads_time_series
Read-only

Returns the company's ad spend, impressions, clicks and conversions over time in a date range, for total ad spend or a spend trend chart. start and end are full ISO 8601 timestamps such as 2026-04-01T00:00:00Z; omit both for the last 90 days. Call get_ecommerce_connection_status first and answer together with it: never report zero for a platform whose data is still syncing or not connected. It reads the active company; for another company the user owns, pass its companyId from list_companies instead of switching the active company.

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_ads_time_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoOPTIONAL end as a FULL ISO 8601 timestamp WITH time + timezone, e.g. '2026-04-30T23:59:59Z'. Never date-only. Omit alongside `start` to fall back to the rolling 90-day window.
startNoOPTIONAL start as a FULL ISO 8601 timestamp WITH time + timezone, e.g. '2026-04-01T00:00:00Z'. Always include the time component and Z suffix — date-only strings (like '2026-04-01') are rejected by the upstream service. If the customer doesn't specify a date range, OMIT this and the tool defaults to the last 90 days.
contextNoOptional, for analytics only. In one sentence, why you are calling this tool and how it serves the user's goal. Describe the purpose in general terms: never include names, emails, phone numbers, addresses, IDs or any other personal details.
companyIdNoOPTIONAL. The doolaCompanyId (an id like '30E5c1AQA326uOuDlsic4No7zZ5'). LEAVE THIS EMPTY/UNSET to use the customer's currently active company — that is the correct default for almost every question. Pass a value ONLY when the customer explicitly references a *different* company they own (e.g. 'show me transactions for my other company X'). NEVER pass a company name, slug, or human label here — only an exact id string.
llm_modelNoOptional, for analytics only. Your exact model identifier from your system prompt (e.g. "claude-opus-4-8"), or "unknown" if unsure. Never guess.
conversation_idNoOptional, for analytics only. The exact conversation_id from this server's previous response, unchanged. The first response provides one, so leave this out until you have it and never invent one. Keep passing the same value for the rest of the conversation, even when the user moves on to a new request.

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 declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description goes further by disclosing the data-quality caveat about syncing/unconnected platforms, the 90-day default window, and which company context is implicitly resolved. Those are exactly the behaviors that cause wrong answers if unknown.

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 what the tool returns, then the parameter convention, then the prerequisite, then the company scoping rule — a sensible order with no filler. The phrase 'for total ad spend or a spend trend chart' is slightly vague about the two output modes and costs a little precision.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still characterizes the returned metrics at a high level, and it covers the prerequisite dependency an agent must satisfy before reporting numbers. It does not state the series granularity (daily vs. weekly) or the response shape, which leaves a modest gap for a time-series tool.

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 schema already documents the ISO 8601 format requirement, the omit-both fallback, and the companyId semantics in detail. The description restates the date convention and the companyId fallback without adding syntax or constraints beyond the schema, so the baseline 3 applies.

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 first clause names a specific verb and resource set — ad spend, impressions, clicks, and conversions returned as a time series over a date range — which is clearly distinct from sibling tools like get_ads_campaigns (campaign breakdown) and get_orders_time_series (a different metric family). An agent can route to it without opening the schema.

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?

It gives explicit prerequisites (call get_ecommerce_connection_status first and answer together with it), explicit defaults (omit both dates for the last 90 days), and an explicit alternative path for a different company (pass companyId from list_companies rather than switching the active company). It also names the when-not case: never report zero for a syncing or unconnected platform.

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.