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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's job is added context, and it delivers: there is no server-side resume, the user must resume in SMS Everyone, and a running campaign likely completes first. What it omits is what state the campaign lands in and what the call returns, which matters for a destructive write.

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 short sentences, front-loaded with the WRITE marker and the core action before caveats. The trailing REST endpoint note is marginally useful but is the one sentence that could be trimmed without loss to the agent.

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?

Covers preconditions, irreversibility and the real-world race with fast sends, which is what an agent needs before a destructive write. No output schema exists and the description doesn't indicate the response shape or resulting campaign status, a minor remaining gap.

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 both parameters, including the confirm gate, are fully documented in the schema. The description adds no parameter-level detail (e.g. how to obtain campaign_id beyond the schema text), so baseline 3 applies.

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?

Opens with 'WRITE: pauses a scheduled campaign (or one that is sending)', giving a specific verb, resource and mutation class in the first clause. The parenthetical about send speed makes clear this is a pause-not-cancel operation, separating it from smseveryone_cancel_campaign conceptually even without naming it.

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?

States a concrete precondition ('a campaign scheduled in the past cannot be paused') and the practical consequence of calling on a running campaign. It does not explicitly route to cancel_campaign or get_campaign_status when pausing is wrong, so the alternative-selection guidance is implied rather than spelled out.

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