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

Beyond the destructiveHint/openWorldHint annotations, it discloses the two-phase confirmation behavior: a missing or false confirm_budget_impact returns requires_confirmation and proposed_changes with no write. It also states the real-world consequence of restart (resuming advertising spend), which is genuine added context for a destructive, open-world mutation.

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 sentences, front-loaded with the core action and then the conditional flag rule; little waste. A minor overlap exists between the second and third sentences about the confirmation flag, but overall it is tight.

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, the description does state the response shapes (platform operation result, validation error, or a confirmation payload), which is the key missing piece. It could go further on what the confirmation payload contains beyond proposed_changes, 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 coverage is 100% and the schema already documents each parameter, including the restart-only requirement for confirm_budget_impact. The description's parameter information largely restates that, so it sits at the baseline rather than adding new semantics such as ID format or budget-unit expectations.

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?

"Pause or restart a campaign by ID" gives a specific verb pair and resource, and the two-action scope separates it from siblings like archive_campaigns, launch_campaign, and duplicate_campaign without needing to open the 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 clearly explains the conditional path for restart versus pause and what happens with the confirmation flag, which is the main usage decision an agent faces. It stops short of naming sibling alternatives (e.g., archive_campaigns for permanent removal) or saying when this tool should not be used.

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