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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real substance beyond them: it validates operation kind, approval integrity and state drift before sending, and forbids replay when the outcome is uncertain. It still doesn't say what specifically is mutated or what a success returns, but the pre-flight verification context is valuable.

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, front-loaded with the action and effect before the preconditions and reconciliation rule. Every sentence adds information; only the slightly awkward phrasing of the opening clause costs it a point.

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 destructive confirm-style mutation with no output schema, the description covers the effect, the required prior step, the pre-send validation, and the no-replay policy, with annotations covering the safety profile. The undocumented connection_context parameter is the main remaining gap.

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% – customer_id is documented, but draft_id and connection_context are bare in the schema. The description compensates partially by defining draft_id as a draft produced by the prepare tool, yet says nothing about connection_context or the required format of draft_id, so the gap is not fully closed.

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 (confirm the scheduling of a Search experiment) and clarifies the effect: it 'starts serving'. It also names its prepare counterpart, letting an agent separate it from google_ads_experiment_schedule_prepare and from the other experiment_*_confirm siblings.

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 a clear precondition: it 'accepts only a matching draft from google_ads_experiment_schedule_prepare', which tells the agent to call prepare first and to reuse that draft. The reconciliation sentence further steers behavior on uncertain outcomes, though it does not name google_ads_mutation_reconcile as the alternative.

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