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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the safety profile is known. The description adds nuance beyond the schema's generic 'confirm' text by narrowing the confirmation gate to bid/target increases specifically, which changes how the agent sequences the call. It still doesn't say what happens if confirm is omitted on a raise, or whether changes can be reverted.

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 sentences, no filler, and the action set is front-loaded ahead of the confirmation constraint. Every clause carries information the agent needs.

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?

For a live destructive mutation the description is serviceable but thin: it never states that the change takes effect on a real Google Ads account immediately, nor what a successful or rejected call returns (no output schema exists). The dry_run escape hatch is documented only in the schema, so an agent reading the description alone may miss the safe-preview path.

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 43% schema description coverage, the description compensates by mapping three undocumented parameters to their meaning: name for rename, cpc_bid as default max CPC, and target_cpa as the target. account, ad_group_id, dry_run and confirm are left to the schema, which does describe the latter two, so the remaining gap is minor.

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 gives a specific verb plus resource ('Rename an ad group') and enumerates the exact fields it can change (default max CPC, target CPA), so the agent knows this is a settings mutation on an existing ad group. It does not explicitly contrast with nearby siblings like google_ads_update_campaign or google_ads_set_keyword_bid, but the ad-group scope is unambiguous.

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 adds one real usage rule: raising a bid or target requires user confirmation in chat. It gives no guidance on when to prefer this tool over sibling mutators (update_campaign, set_keyword_bid, update_ad) and no prerequisites such as needing the ad group to already exist.

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