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

The annotations only carry destructiveHint=true, readOnlyHint=false, and openWorldHint=true; the description adds substantial behavioral context well beyond these. It discloses that operations push to the live ad channel, that remove_all is permanent, that clean_resubmit_all is refused when the connection is down, and that pre_pair is non-destructive. It also explains the returned status values such as 'not_allowed' under Auto-Pilot mode.

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?

The description is dense but every sentence adds operational value: scope, alternatives, per-operation behavior, hazards, confirmation requirements, return shape, and prerequisite context. The most critical scoping constraint is front-loaded before the operation details and no information is redundant with the annotations or schema.

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 complex, destructive whole-integration operation with 4 parameters and no output schema, the description covers all essential decision points: when to use it, what each operation does, hazards, confirmation rules, mode-specific behavior, return fields, and how to resolve the optional project_id. An agent has enough context to select and invoke the tool correctly without additional lookups.

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?

The schema only documents ad_id and operation, leaving confirm and project_id at 50% coverage. The description compensates fully: confirm is tied to destructive operations requiring user confirmation, project_id is optional unless the project requires it, and every operation enum value is semantically explained. This exceeds what the schema provides.

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?

Clearly identifies a specific verb ('run'), a resource ('ad integration'), and a defining scope: it acts on the whole integration, not a subset. It explicitly contrasts itself with run_ad_item_action, so an agent can distinguish sibling tools without opening schemas.

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?

States exactly when to use this tool versus run_ad_item_action, and gives conditional usage guidance: submit_all only works in manual product mode, clean_resubmit_all has a ~5 minute cooldown, and destructive operations require confirm:true after user confirmation. It also tells the agent to call list_projects when project_id is required, routing to the right prerequisite tool.

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