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

Annotations only declare non-read-only, non-destructive, non-open-world, which does not reveal that pausing an archived campaign silently unarchives it — a genuine side effect the description surfaces. The prerequisite for "active" is also an operational constraint not present in structured data. It does not say whether setting status to the value it already holds is a no-op or what errors occur when the precondition fails.

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, zero filler, with the primary action first and the constraint/side-effect disclosures stacked behind it. Every clause carries operational information.

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?

Only two required parameters, one of them a plain 24-char ID, and an output schema exists, so return-value explanation is unnecessary. The description covers the transition semantics and the one surprising side effect, which is enough for an agent to call this 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 50% (campaignId is documented, the status enum values are bare), and the description compensates by explaining what the "active" and "paused" values actually require and do. It adds real meaning beyond the enum list rather than restating it.

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?

The description names a specific verb (turn on/pause/archive) and resource (campaign) and enumerates the three target states, so an agent knows exactly what the tool mutates. It stops short of naming the adjacent sibling campaigns_update to say which tool handles other field changes, so sibling differentiation is only implicit from the name.

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?

"active needs a sender pool with an active inbox" states a concrete precondition an agent must check before invoking, and the archived-campaign behavior tells the agent what state transition is legal. There is no explicit exclusion like "use campaigns_update to rename a campaign", so alternatives are not covered.

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