Update ad group

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

Annotations only say the tool is not read-only and is open-world. The description adds meaningful behavioral detail: this is a partial update, unspecified fields are left unchanged, and monetary fields require confirm=true. It does not cover error cases or consequences of missing confirm, but it discloses the main side-effect guardrails.

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 three short, front-loaded sentences that each carry distinct information: operation scope, PATCH behavior, and money-field confirmation. There is no filler, no repetition of schema field names, and every sentence earns its place.

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?

The core update semantics are present, including the critical partial-update rule and confirm requirement. But with 7 parameters, no output schema, and minimal schema descriptions, the missing meaning of line_item_id, the role of confirm when false, and expected return/error behavior make this adequate rather than complete.

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?

With only 14% schema description coverage, the description must compensate, and it does clarify the updateable fields: name, bid, budget micros, and confirm. However, it never explains what the required line_item_id refers to or where it comes from, and it does not define 'micros' precisely, leaving a meaningful parameter-semantics gap.

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 states the exact operation and scope: a partial update of name, bid, and/or budget micros on an ad group. It also communicates PATCH semantics through 'Only change what the user named,' which distinguishes it from full-replacement or creation tools.

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?

It implies when to use it: when the user wants to modify only specific ad-group fields rather than replace the entity. However, it does not explicitly name alternatives or exclusions, such as when to prefer x_ads_update_campaign or x_ads_set_status instead, leaving some selection logic to inference.

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