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

Goes far past the annotations (readOnlyHint=false, destructiveHint=true, consistent with the write flow): it discloses the two-step preview/confirmation_token protocol, token expiry and invalidation on argument change, that ad spend already incurred cannot be undone, the undo path, the five data_availability outcomes, and a prompt-injection caveat. It also discloses the per-call token cost.

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?

Purpose and the mutable fields are front-loaded, and nearly every sentence carries distinct operational information. It is dense (a single unbroken block of ~10 sentences, with the data_availability legend and boilerplate safety warning that recur across this tool family), which slightly dilutes focus, but little is truly wasted.

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?

There is no output schema, so the description must explain returns — and it does: 'The result gives the previous values; to undo, update again with them', plus the data_availability taxonomy and the fact that no_rows/access_error do not mean zero. For a destructive, budget-touching write tool, an agent has everything needed to call it safely.

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 100% schema coverage the baseline is 3, but the description adds a real constraint the schema does not express — that at least one of name/status/daily_budget_amount must be sent and that an unchanged value is silently dropped. It also clarifies currency unit semantics for daily_budget_amount (won for KRW, no currency sign), buying real meaning beyond the schema text.

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?

Opens with a specific verb+resource+scope: 'Update one Display campaign in the selected Google Ads account', then enumerates exactly the three mutable fields (name, status, daily budget). It also implicitly separates itself from the other campaign-type update siblings by stating that 'a campaign of another type ... is refused', so an agent can tell it apart from search/pmax/demand_gen update 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 clear when-to-use rules ('Send at least one of them; a value equal to the current one is not sent') and explicit when-not conditions ('Do not call again when the result is unknown', other campaign types / removed campaigns / shared or non-daily budgets are refused). It stops short of naming the concrete sibling (e.g. google__ads__search__campaign__update) as the alternative, which keeps it from a 5.

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