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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the bar is lower, yet the description still adds real value: it discloses that the campaign is created paused and that exactly one ad group and one ad are produced, which tells the agent a follow-up enable step is needed. It does not mention that image vs video is mutually exclusive or what happens if both asset sets are supplied.

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?

Three short clauses, front-loaded with the campaign type and constrained ad structure; every sentence carries information (surfaces, the two ad variants, channel selection, paused state) with no filler.

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 24-parameter, 8-required mutation tool with no output schema and thin schema coverage, the description is too sparse: it never explains the required targeting/creative fields, budget/bidding interplay, the image-vs-video exclusivity, or what the tool returns (campaign ID?) so the agent can chain google_ads_enable_campaign.

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 24 parameters and only 25% schema description coverage, the description carries most of the burden but documents only the asset-bearing parameters (landscape/square/portrait images, logos, youtube_videos) and channels. Bidding, max_cpc, target_cpa, target_roas, daily_budget, locations, languages, headlines, descriptions, long_headlines, call_to_action, user_list_ids, user_interest_ids and dry_run are left entirely to the schema.

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?

States a specific verb and resource ('Create a Demand Gen campaign') and enumerates the surfaces it targets (YouTube, Discover, Gmail, Display), plus the structural payload it generates: one ad group and one ad. It implicitly separates itself from the Display/PMax/Search creation siblings by naming the campaign type and the asset shapes, though it never explicitly names those alternatives.

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?

Gives one useful routing cue — 'Pick channels for YouTube-only' — and a lifecycle note ('Always PAUSED'), but says nothing about when to choose this tool over google_ads_create_display_campaign, google_ads_create_pmax_campaign, or google_ads_create_ad_group instead. No prerequisites (account access, asset approval) are mentioned.

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