Skip to main content
Glama

Google Ads: update campaign settings

update_campaign
DestructiveIdempotent

Updates an existing Google Ads campaign's settings.

Changes apply at once to a running campaign: a higher budget, a later
end date, or switching on search partners or the Display Network can
show its ads to more people and raise what it spends.

search_partners, display_network and geo_target_type change the same
three settings create_campaign sets, so a campaign created earlier, or
created outside this server, can be changed here; PRESENCE targets only
people in the targeted locations. Each is applied only when passed.
languages applies to Performance Max and Display campaigns, including
one created outside this server; a campaign with no language setting
may show to people who use any language.

languages sets exactly the given list: languages the campaign has that
are not in it are removed, missing ones added, and the result reports the
campaign's languages before and after (an empty list means every
language). Read the campaign's current languages first and pass every
language to keep: a language left out of the list is removed. Read them
with search: resource campaign_criterion, fields campaign.id,
campaign_criterion.language.language_constant, conditions campaign.id =
<campaign_id>, campaign_criterion.type = 'LANGUAGE',
campaign_criterion.status != 'REMOVED'. Performance Max uses the setting
on YouTube, Display, Discover and Gmail, not on Google Search.
Search campaigns have no language setting: Google Ads removed it in late
September 2026 and matches Search ads by the language they are written
in, so languages is refused on a Search campaign. Language criteria an
older Search campaign still carries are returned by reads but no longer
used by Google. languages is refused on a Video campaign too, before
anything is sent: the Google Ads API cannot change Video campaigns, so
their languages are changed in Google Ads. A languages change and the
other campaign settings in the same call are applied together or not at
all; a budget change is a separate request, sent first.

bidding_strategy_type switches the campaign to a standard bidding
strategy, replacing the one it has (including a portfolio strategy). The
usual fix for a new Search campaign that is not winning auctions on manual
CPC is TARGET_SPEND (Maximize Clicks) with a cpc_bid_ceiling_micros cap.
Supported, by campaign type — anything else is refused before any change:
  SEARCH: MANUAL_CPC, TARGET_SPEND, MAXIMIZE_CONVERSIONS, TARGET_CPA,
    MAXIMIZE_CONVERSION_VALUE, TARGET_ROAS.
  DISPLAY: MANUAL_CPC, TARGET_SPEND, MAXIMIZE_CONVERSIONS, TARGET_CPA,
    TARGET_ROAS. Google does not offer MAXIMIZE_CONVERSION_VALUE
    without a target ROAS on Display campaigns.
  PERFORMANCE_MAX: MAXIMIZE_CONVERSIONS, TARGET_CPA,
    MAXIMIZE_CONVERSION_VALUE, TARGET_ROAS.
  MULTI_CHANNEL (App): the strategy the campaign already has, with a
    new target — TARGET_CPA with target_cpa_micros, TARGET_ROAS with
    target_roas. An App campaign's strategy follows its app bidding
    goal, so a different strategy is refused here.
Moving to TARGET_SPEND requires cpc_bid_ceiling_micros. Re-sending
TARGET_SPEND without a cap on a campaign already using it keeps the
existing cap; nothing clears a cap. For the conversion strategies a target
left out is cleared (e.g. MAXIMIZE_CONVERSIONS removes a target CPA).

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    campaign_id: The ID of the campaign to update.
    name: New campaign name. Optional.
    budget_amount_micros: New daily budget in micros of the account's currency (10000000 = 10.00: ₹10 on an INR account, $10 on a USD one).
        On a budget shared by several campaigns the new amount applies
        to all of them; the result's budget_shared says how many.
        Optional.
    start_date: New start date in YYYY-MM-DD format. Optional.
    end_date: New end date in YYYY-MM-DD format. Optional.
    search_partners: False stops the campaign serving on the Google Search
        Partners network, True allows it. Optional.
    display_network: False stops the campaign serving on the Google
        Display Network, True allows it. Optional.
    geo_target_type: New positive location targeting. One of: PRESENCE
        (only people in the targeted locations), PRESENCE_OR_INTEREST
        (also people elsewhere who show interest in them), SEARCH_INTEREST.
        Optional.
    bidding_strategy_type: New bidding strategy. One of: MANUAL_CPC,
        TARGET_SPEND (Maximize Clicks), MAXIMIZE_CONVERSIONS, TARGET_CPA
        (Maximize Conversions with a target cost per conversion),
        MAXIMIZE_CONVERSION_VALUE, TARGET_ROAS (Maximize Conversion Value
        with a target return on ad spend). See the list above for which
        campaign types accept which. Optional.
    cpc_bid_ceiling_micros: Maximize Clicks' max CPC cap — the most
        Google may bid for one click — in micros of the account's currency
        (10000000 = 10.00: ₹10 on an INR account, $10 on a USD one). Only
        with TARGET_SPEND; required when moving to it, optional (the
        existing cap is kept) when the campaign already uses it.
    target_cpa_micros: Target cost per conversion in micros of the
        account's currency (10000000 = 10.00: ₹10 on an INR account, $10
        on a USD one). Required with TARGET_CPA, refused otherwise.
    target_roas: Target return on ad spend as a ratio (e.g., 2.0 for
        200%). Required with TARGET_ROAS, refused otherwise.
    languages: Google Ads language codes (e.g. en, hi, es, pt, de, fr,
        ja, zh_CN); sets exactly this list, removing the rest, so pass
        every current language to keep. ["all"]
        removes every language setting. Performance Max (used on YouTube,
        Display, Discover, Gmail; not on Google Search) and Display
        campaigns only; refused on Search and Video. Optional.
    over_comfort_ack: The user's own words or reason when they asked for
        a budget above their saved comfort (e.g. "user asked for 6,000/day
        on 2026-09-23"). Recorded with the change by the hosted connector;
        never sent to Google. Optional.

Returns:
    Dictionary with the updated resource names and a confirmation message;
    with languages, also languages: {before, after, changed}; with a
    budget shared by several campaigns, also budget_shared: {campaigns}.

Tools revision: d80f65c0.

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": {
      "customer_id": "<customer_id>",
      "campaign_id": "<campaign_id>"
    },
    "name": "update_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
end_dateNo
languagesNo
start_dateNo
campaign_idYes
customer_idYes
target_roasNo
display_networkNo
geo_target_typeNo
search_partnersNo
over_comfort_ackNo
target_cpa_microsNo
budget_amount_microsNo
bidding_strategy_typeNo
cpc_bid_ceiling_microsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructive and idempotent, but the description adds substantial context beyond them: budget changes propagate to all campaigns sharing a budget, languages is a full replacement that removes omitted languages, a languages change is atomic with other settings while the budget change is a separate request sent first, and over_comfort_ack is recorded locally and never sent to Google. These are exactly the risk details an agent needs before mutating a live campaign.

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 spend-risk warning is correctly front-loaded and the paragraphs are organized by concern, but the text is long and repeats itself: the languages replacement semantics appear both in prose and again in the Args entry, the Performance Max channel list is given twice, and the PRESENCE definition is duplicated in prose and in geo_target_type. Trimming those redundancies would preserve all the meaning at materially shorter length.

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?

For a 15-parameter destructive mutation tool, the definition covers campaign-type applicability, refusal conditions, atomicity, shared-budget side effects, and even a Returns section describing the languages before/after and budget_shared payloads. Nothing an agent needs to invoke it safely appears to be missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden, and it does: micros conversion is explained with worked currency examples, enum values for geo_target_type and bidding_strategy_type are spelled out, and conditional requirements are stated (target_cpa_micros required with TARGET_CPA and refused otherwise, cpc_bid_ceiling_micros required when moving to TARGET_SPEND but preserved on re-send).

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 line gives a specific verb and resource ("Updates an existing Google Ads campaign's settings") and the body enumerates exactly which settings are in scope. It also distinguishes itself from create_campaign by noting the three settings it shares with it, so an agent can place it among siblings 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 states when to use each setting, including the explicit prerequisite to read current languages via the search tool before passing languages, and the recommended fix for a Search campaign on manual CPC (TARGET_SPEND with a cpc_bid_ceiling_micros cap). It also names the conditions under which the call is refused (Search and Video campaigns for languages, unsupported bidding strategies per campaign type), which is genuine 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