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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but they cannot convey the two-step dry-run/confirm protocol. The description discloses this critical behavior — that a default call produces no mutation — which an agent could not learn from annotations or schema alone.

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?

Two short sentences; the action is front-loaded and the second sentence carries only the non-obvious confirm semantics. No filler.

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?

Output schema exists, so return values need no explanation, and annotations cover the destructive profile. The description adequately completes the behavioral picture, though it omits prerequisites such as which ad platform connection/account type this applies to.

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 0%, so the description must carry parameter meaning. It explains the most consequential parameter, confirm (default false, preview vs. real pause), but says nothing about campaign_id or customer_id, which are required. Partial compensation warrants a 3.

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 (pauses) and resource (campaign) plus the required confirmation step. However, it does not distinguish itself from the many sibling status-mutation tools (update_campaign_status, update_tiktok_campaign_status, update_meta_campaign, etc.), leaving the agent to infer which pausing tool applies.

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 conditional usage instruction: confirm=false returns a preview only, confirm=true performs the pause. It does not name an alternative tool for changing campaign status in other ways, so the 'when not to use' dimension is absent.

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