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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's main added value is the 'Created PAUSED' disclosure, which is genuinely important. However, it says nothing about atomicity on partial failure (e.g., ad group created but ad rejected), whether a budget or bid is required, or validations that may reject the request.

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?

Two short, front-loaded sentences with zero filler; the most decision-relevant fact (created PAUSED) is given last for emphasis rather than buried.

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?

An 11-parameter mutation tool with nested keyword objects, array min/max constraints, no output schema, and almost no schema documentation — the description does not come close to filling that gap. An agent would not know from this text whether headlines/descriptions/final_url are effectively mandatory for the ad to succeed.

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?

Schema description coverage is only 18% (account and dry_run are the only documented properties), so the description could have compensated but does not. It mentions keywords and a responsive search ad, which loosely maps to the keywords/headlines/descriptions arrays, but adds no constraints such as headline length limits, required final_url, or cpc_bid interaction with campaign bidding.

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?

Names a specific verb and resource (add an ad group to an existing campaign) and states the compound payload it bundles: keywords plus a responsive search ad. That composite scope distinguishes it from single-purpose siblings like google_ads_create_ad or google_ads_add_keywords, though the description never names those siblings explicitly.

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 phrase 'to an existing campaign' implies a prerequisite (campaign_id must already exist) and the compound nature implies when to prefer this over separate keyword/ad calls, but nothing is stated as an explicit when-to-use rule. There is no guidance on when to use dry_run or whether this should be followed by an enable/status call.

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