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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered by structured data. The description adds the returned field inventory but says nothing about pagination, result caps, or what happens when the status default of ALL excludes removed campaigns — context that only appears in the schema.

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, front-loaded with the resource and the field list, and ending on the actionable caveat. No filler or restatement of the title.

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?

With no output schema, the description usefully compensates by naming the returned fields, and the 'use before changing' note covers the tool's role in a read-then-write workflow. Minor gaps remain around result volume and default account resolution, both partially handled by the schema.

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 100%, with folder, status (enum, default ALL except removed) and account all documented inline, so the schema carries parameter meaning. The description adds no filtering semantics of its own — notably it never mentions that results can be scoped by folder versus account.

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 ('List campaigns') and enumerates the exact settings returned (status, serving status, channel type, bidding strategy and tCPA/tROAS targets, budget, dates, networks). This clearly separates it from google_ads_performance or google_ads_update_campaign, though it never names a sibling to differentiate against explicitly.

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?

'Use before changing anything' gives a concrete sequencing rule that tells the agent this is the pre-mutation read step, which is genuinely actionable given the many google_ads_update_*/set_*/pause_campaign siblings. It stops short of naming those alternatives or stating when not to use it (e.g. versus google_ads_campaign_targeting).

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