Google Ads MCP Server

update_budget

Idempotent

Update an existing Google Ads campaign budget, including amount, name, or delivery method, with a preview and confirmation before spend-affecting changes are applied.

Instructions

Update an existing campaign budget.

Safety: changing the amount or delivery method returns a preview first
(current vs new amount); call again with confirm=True to apply. Renaming
only is applied immediately. Refused if the new amount breaks
GOOGLE_ADS_MAX_DAILY_BUDGET or GOOGLE_ADS_MAX_BUDGET_INCREASE_PCT.

Args:
    customer_id: Google Ads customer ID.
    budget_id: Budget ID to update.
    amount: New daily budget amount in currency.
    name: New budget name.
    delivery_method: New delivery method -- 'STANDARD' or 'ACCELERATED'.
    confirm: Must be True to apply an amount or delivery change.

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>",
      "budget_id": "<budget_id>"
    },
    "name": "update_budget"
  }
}

Input Schema

Name	Required	Description	Default
`name`	No
`amount`	No
`confirm`	No
`budget_id`	Yes
`customer_id`	Yes
`delivery_method`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 11, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: a two-phase preview/confirm flow, the contents of the preview (current vs new amount), the immediate-apply exception for renames, and the guardrail variables that can cause refusal. This is fully consistent with destructiveHint=false and idempotentHint=true, since a confirm-gated apply is non-destructive and repeatable.

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-loads the purpose, then a clearly labeled Safety block, then the parameter list. Every sentence is load-bearing. The Args entries partly restate the schema property names, which is justified here only because schema coverage is zero.

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, and the description covers the return behavior by explaining the preview payload and the confirm step. For a mutating tool with a conditional two-call protocol and server-side validation limits, nothing an agent needs in order to call it correctly is 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: every one of the six parameters is explained in the Args block, including the enum values 'STANDARD' or 'ACCELERATED' for delivery_method, the units for amount, and the precondition on confirm. This adds meaning well beyond the bare schema types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Update an existing campaign budget.' That clearly separates it from create_budget and from campaign-level tools like update_campaign. It stops short of naming an alternative tool for budget edits, so it is clear but not maximally differentiated.

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 when-to guidance: amount or delivery changes trigger a preview and require a second call with confirm=True, while rename-only changes apply immediately. It also states the rejection condition against the two max-budget settings. It does not point to sibling tools, but the operational conditions an agent needs are explicit.

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

Deploy Server