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

Annotations already declare readOnly=false, idempotent=true, destructive=false, but the description adds the crucial consequence an agent could not infer: live enrolls every matching contact and sends them real email, and pausing stops all sending until it is live again. It also discloses the failure mode (fails with the first readiness problem), which is exactly the behavioral context the idempotent/destructive hints omit.

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 with the action, then the safety gate, then the transition table, then the failure mode — a sensible ordering. The sentence enumerating all three transitions is slightly redundant with the opening line but earns its place by removing ambiguity.

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 2-parameter mutation with no output schema, this covers the action, the precondition, the per-state effect and the error surface. Only the success return value is left implicit, which is minor given there is no output schema to explain.

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 description coverage is 0% and the schema only constrains status to three bare constants, so the description carries the meaning: draft→live, live→pause, paused→live. That is genuinely additive, though campaign_id is never explained (its meaning is obvious from the name).

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 specific verbs and a resource ('Start, pause or restart a campaign') and then spells out the three state transitions, so an agent can distinguish this mutation from update_campaign or set_broadcast_status without opening a 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 an explicit precondition that gates the dangerous path: live 'only set it after the user has seen the campaign and its audience and said yes.' It also points at get_campaign_readiness as the way to surface the same problems before going live, which routes the agent to the right sibling.

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