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 description's main added value is the "Always created PAUSED" guarantee — a genuine behavioral trait that tells the agent the new campaign will not spend until enabled. It also discloses the hard asset/character constraints enforced at creation. It stops short of noting the required account/permission context or what is returned on success.

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 action and the campaign type, then a single dense enumeration of requirements with no filler sentences. It is packed into one sentence where a short list would scan better for 18 parameters, but nothing is redundant.

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 an 18-parameter, 11-required creation tool with no output schema, the description covers the creative and targeting essentials but omits account selection, dry_run validation, and how target_cpa/target_roas must match the chosen bidding strategy. It also says nothing about what happens on partial asset failure or what the caller receives back.

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 17%, so the description carries most of the burden and does well: it adds minima the schema omits (3–15 headlines, 1–5 long headlines, 2–5 descriptions with one ≤60 chars) and detailed image dimension/ratio requirements per array. It leaves account, dry_run, and the target_cpa/target_roas pairing with the bidding enum undocumented, which is the main gap.

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 Performance Max campaign") plus the structural scope ("with one asset group"). The Performance Max qualifier is enough to separate it from the many sibling create_*_campaign tools (search, display, shopping, demandgen, app) without opening any schema.

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?

Implies usage via "Always created PAUSED," which hints that enabling requires a follow-up call (google_ads_enable_campaign), and notes search themes are optional. However, it never states when to pick this over google_ads_create_search_campaign or when to use google_ads_pmax_asset_group / google_ads_add_assets to extend an existing campaign instead.

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