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

Goes well beyond the annotations by disclosing that the campaign is ALWAYS created paused, that the preview sends the real request to Google while creating nothing, and that videos cannot be uploaded here. These are non-obvious side effects an agent must know before invoking a mutation with destructiveHint=false and idempotentHint=false. It stops short of describing what the preview response contains or what happens on partial failure.

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?

Front-loaded with the core action and scope, then the paused constraint, then the preview/confirm loop, then prerequisites and sibling routing. Every sentence supplies distinct information with no repetition of schema content.

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 20-parameter, 10-required mutation with no output schema, the description covers the decision-critical gaps: safety (always paused), the confirm gate, landing-page acknowledgement, external prerequisites (YouTube upload), and where to go for follow-up edits. Nothing essential to invoking it correctly is missing.

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 coverage is already 90%, so the parameter definitions carry most of the load. The description still adds workflow-level meaning the schema cannot express: the preview validates images, text and bid; the budget should be surfaced alongside a monthly equivalent; and geo_target_ids drive the locations shown to the user. It does not add much for the remaining fields such as channels or long_headlines beyond what the schema states.

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 ('Build a whole Google Ads Demand Gen campaign') and enumerates exactly what gets created in one step: daily budget, campaign, ad group with locations, and the first image or video ad. It also distinguishes itself from siblings by pointing to ads_create_demand_gen_ad for additional ads, so an agent can separate this from the narrower ad-level and campaign-level 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?

Gives explicit operating instructions: preview first, show the user the budget, monthly equivalent, locations and ad verbatim, then call again with confirm true. It also names the alternatives (ads_create_demand_gen_ad for more ads, ads_set_ad_url for URL changes) and states the prerequisite that videos must already be on YouTube.

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