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

Annotations already declare destructive=true, idempotent=false and openWorld=true; the description adds genuinely new behavioral facts: the approval gate, the confirmed=true requirement before credit use, the unrecoverable ended-state restriction, and that writes are never auto-retried. Those are exactly the traits an agent needs before calling a destructive, credit-consuming 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?

Front-loaded and only four short sentences, with the safety-critical constraints placed early. The opening 'Resume campaign.' merely restates the name/title and is redundant with the sentence that follows, a minor waste.

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, non-idempotent mutation with no output schema, the definition covers preconditions, approval, and retry semantics, which is most of what matters. It says nothing about what resuming actually does to recipients, scheduled sends, or credits consumed, leaving some behavioral consequence unexplained.

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 50%, but both fields carry descriptions; the description nevertheless adds meaning by tying confirmed=true to an external user-approval event and to credit usage, which the schema's field text does not state. The nested path.id parameter is left to the schema's 'Resource ID' label, a small remaining gap.

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 and resource ('Resume a paused campaign') and immediately bounds the scope with 'An ended campaign cannot be resumed.' That precondition is what distinguishes it from the sibling pause/end/cancel operations, so an agent can select it without opening 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?

Gives a clear usage condition — only paused campaigns, never ended ones — plus a hard prerequisite (user approval and confirmed=true) before any change or credit spend. It does not explicitly name alternatives to use for ended campaigns, which keeps it short of a 5.

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