Launch one campaign across platforms; children are created paused, then activated

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds meaningful behavior beyond that — default dry-run safety, the explicit opt-in flag, and the two-phase side effect where children are created paused before activation. It stops short of describing failure behavior for invalid briefs, partial platform failures, or what the launch response reports.

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 destructive-triggering detail front-loaded, and no filler. The endpoint path is a useful anchor and costs almost nothing.

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?

The critical semantics (default-safe dry run, confirm, paused children) are covered, so an agent can call it safely. But for a high-complexity fan-out write with a large required brief and no output schema, the description says nothing about required brief contents, what a dry run returns, or idempotency behavior.

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?

The only parameter insight (confirm triggers real execution) merely restates the schema's own description for confirm, and idempotencyKey is not mentioned at all. The 'body' CampaignBrief — a large, deeply nested object with essentially no field descriptions — is left entirely unexplained, so the description does not compensate for the schema gap on the parameter that matters most.

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 scope: launch ONE campaign across multiple platforms, verbatim 'Launch one campaign across platforms'. The added lifecycle note ('children are created paused, then activated') tells an agent exactly what the operation produces, which distinguishes it from crosspost_preview/crosspost_resolve 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 the crucial conditional: dry run by default, set confirm: true to actually execute. That is real when/when-not guidance for a write. It does not name alternatives (e.g., crosspost_preview for inspection, campaigns_create for single-platform) or state prerequisites like a valid connection per target platform.

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