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

Annotations declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered, but the description adds real behavioral context: 'No action is sent during prepare' clarifies this is a non-mutating staging step, and it explains the effect of each mode. It doesn't describe the resulting snapshot contents or what the caller receives, keeping it below a 5.

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?

Four tight sentences, front-loaded with the action and resource, followed by mode semantics, the no-action guarantee, and the routing note. Every clause carries information; density is high but no sentence is 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?

With no output schema and a nested body object at 33% coverage, the description should explain what 'prepare' produces (e.g., an approval plan) and remaining body fields; it does not. It covers the essential routing, mode semantics, and non-mutation guarantee, making it adequate but with clear gaps.

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 only 33%, so the description must compensate for undocumented parameters. It adds meaning to the 'mode' param by explaining schedule vs promote, and references 'explicit affected campaigns' (affected_campaign_ids), but says nothing about experiment_id, customer_id, connection_context, or the maxItems=2 constraint. Partial compensation justifies the baseline 3.

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+resource ('Prepare native Search experiment schedule/promote') and explicitly identifies itself as a compatibility entrypoint, naming the two named tools that should be preferred. An agent can distinguish it from the sibling *_prepare tools 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?

Explicitly routes the agent away from this tool ('prefer the matching named tool: google_ads_experiment_schedule_prepare, google_ads_experiment_promote_prepare') and distinguishes the two modes by semantics (scheduling starts serving; promoting copies trial settings to control). When-to-use and when-to-prefer-alternatives are both present.

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