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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond that by disclosing that it saves a private draft, runs a Google validate-only pass, captures a complete affected-resource snapshot, and critically does NOT push the change live. That resolves the apparent tension between a non-readOnly tool and a non-destructive one, which is exactly the context an agent needs before invoking it.

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 tight sentences with zero filler, front-loading the action (prepare to schedule, starts serving) before the side-effect disclosure and the approval workflow. Every sentence earns its place.

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 a nested-body mutation-prep tool with no output schema, the description covers the safety model and workflow hand-off well, and nothing is claimed about return values that would need explaining. It could be more complete by summarizing the body contract (which ids are required) or the approval lifecycle, but it is sufficient to call the tool correctly.

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%, so the description is expected to compensate, but it conveys nothing about experiment_id, affected_campaign_ids (including the maxItems=2 and uniqueItems constraints), or the connection_context token. The phrase "affected-resource snapshot" faintly gestures at affected_campaign_ids but adds no usable semantics.

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 to schedule a Search experiment") and explicitly frames the two-step prepare/confirm pattern by naming the sibling google_ads_experiment_schedule_confirm. It also implicitly separates itself from the other experiment_*_prepare tools (halt, promote, initiate) by naming the schedule action, so an agent can distinguish it without opening a 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?

Gives clear routing: this tool does not send the change, and the draft must be shown for explicit approval before calling google_ads_experiment_schedule_confirm. That names the required follow-up tool and the condition that selects it. It does not state when NOT to use it (e.g. vs. experiment_action_prepare or experiment_schedule_confirm directly), so it falls short of a full when/when-not/alternative treatment.

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