get_budgetRead the account's budget and the state of its Emergency Brake: the configured amount and period, the derived daily/monthly caps, the currency, whether the brake is armed, and whether it is currently engaged (and which campaigns it paused). Read-only. Scoped to the active Space.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation is reinforced and expanded by the description, which details exactly what is returned (budget config, caps, currency, brake state, paused campaigns). It also discloses the scope constraint (active Space). This adds meaningful behavior beyond the annotation alone.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four short sentences with a clear front-loaded verb and resource. The long list of return values is necessary and organized with colons and commas, avoiding redundancy. The 'Read-only' phrase is slightly redundant with the annotation but still brief.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Even without an output schema, the description enumerates all the data the tool returns, including budget, caps, currency, and brake engagement details. It also specifies the active Space scoping. For a getter with no parameters, this is fully sufficient to understand behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so schema coverage is trivially 100%. The description's reference to the active Space is a contextual scoping, not a parameter. With no parameters, the baseline score of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads the account's budget and Emergency Brake state, listing specific attributes. However, it does not explicitly distinguish itself from the sibling get_brake_status, which likely covers the brake-state portion. The verb and resource are specific, but sibling differentiation is absent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description notes the operation is read-only and scoped to the active Space, providing clear context for when to invoke it. It doesn't mention alternatives or exclusions, such as using get_brake_status for brake-only queries. Thus it offers clear context but no explicit alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools follow a clear resource+action pattern (get_ad, update_ad, delete_ad), so entity-level tools are easy to distinguish. The main ambiguity is among reporting/status tools like get_conversion_status, get_conversion_health, get_conversion_report, and account_summary vs. get_performance_stats, which could tempt misselection without reading descriptions.
Naming is highly consistent: nearly every resource has create_/get_/update_/delete_/list_ variants, with predictable special verbs like set_, trigger_, preview_, and upload_. Minor exceptions like account_summary or get_angle_readout still follow the same readable verb-driven style.
83 tools is an extreme surface for an MCP server, even one covering ad management. Most entities have full CRUD plus many custom readouts and report variants, which creates context bloat and makes tool selection unnecessarily expensive for the agent.
The platform covers the full campaign lifecycle: campaigns, ad groups, ads, keywords, assets, business/creative planes, conversion actions, sync, budget, and targeting are all represented. Minor gaps exist—conversion sources have create/list but no get/update/delete, and there is no explicit way to update or remove a conversion source—but these can be worked around.