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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds genuinely non-obvious behavior: newly created ad groups are paused by default, and widening channels is a gated operation requiring confirmation. It still omits what happens on partial failures and whether ads are also created paused, so it stops short of full disclosure.

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 sentences, no filler. The scope qualifier comes first, the three supported operations follow, and the confirmation constraint is placed last where it reads as a guardrail rather than a buried detail.

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 destructive, open-world tool with 19 parameters spread across three distinct actions and no output schema, the description is too thin: it does not map parameters to actions, does not explain how confirm and dry_run interact with the confirmation rule, and says nothing about what is returned. An agent could pick the right action but still fail to assemble a valid call.

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 21% across 19 parameters, so the description must carry the burden, yet it never explains which parameters are required per action (e.g. campaign_id and ad_group_name for add_ad_group versus ad_group_id for add_ad). It only gestures at the asset families ('image or video ad') and channels, leaving headlines, descriptions, call_to_action, final_url, business_name, logos and the three image arrays undocumented in both schema and description.

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 names a specific resource (Demand Gen ad group) and enumerates the three operations that map to the action enum: add_ad_group, add_ad, set_channels. The 'On an existing Demand Gen campaign' qualifier distinguishes it from creation tools like google_ads_create_demandgen_campaign, though it does not explicitly name sibling tools such as google_ads_create_ad_group or google_ads_update_ad_group.

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 establishes the prerequisite context (the campaign must already exist) and adds one concrete rule: widening channels needs confirmation. However, it gives no explicit when-not guidance and never routes the agent to alternatives such as google_ads_create_ad_group or google_ads_update_ad_group, leaving the agent to infer which tool applies to non-Demand-Gen campaigns.

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