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

Annotations only declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description adds substantial context beyond that: a private draft is saved, Google validate-only runs, a complete affected-resource snapshot is captured, and no change is actually sent. That is exactly the behavioral disclosure a prepare-tool needs.

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?

Three sentences, front-loaded with the purpose and scope, then behavior, then the required follow-up step. No filler; every clause (SETUP-only, no serving, validate-only, approval gate) carries meaning.

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 mutating prepare tool, the description covers the essential lifecycle and sequencing. It is slightly thin on the nested body semantics (left to a low-coverage schema) and on how the saved draft is later retrieved, but the core information for correct invocation is present.

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 33% - just customer_id is documented, while the nested body (campaign_id, control_percent, name, suffix) and connection_context have no descriptions. The description never explains these parameters or the meaning of control_percent, so it fails to compensate for the low coverage; only a faint hint comes from 'control/treatment arms'.

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 (prepare to create), a specific resource (a Search experiment with its control/treatment arms), and an explicit scope (in SETUP without starting serving). It also names the sibling it feeds into, google_ads_experiment_create_confirm, so an agent can distinguish prepare from confirm without opening either 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?

The description makes the workflow explicit: it does not send the change, and the draft must be shown for approval before calling google_ads_experiment_create_confirm. Both the when (before confirm, after draft review) and the alternative (confirm) are stated, leaving no inference required.

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