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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is known; the description usefully adds the real-world consequence (delivers to actual subscribers) and the confirm-first requirement. It does not cover permissions, whether sending is reversible, or what happens if the campaign is already sent.

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 sentences, both load-bearing: first the action and its variants, then the risk warning. The critical caution is front-loaded enough to be read before invocation.

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, open-world tool with no output schema, the definition leaves gaps: no indication of what is returned (job/send status, scheduled confirmation), no preconditions (must the campaign be in draft?), and no note on partial failure across audiences or throttled batches.

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 75% and send_strategy's schema description already spells out every mode in more detail than the parenthetical in the description, so that text mostly restates. The nested send_options fields (per_hour, window_hours, timezone defaults) have no schema descriptions and are not clarified in prose either.

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 ("send a campaign to its audiences") plus the two modes, immediate send vs. scheduled via scheduled_at. The resource specificity separates it from send-email, but the description never names an alternative sibling explicitly.

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 clear operational guidance: "confirm with the user first" because it delivers to real subscribers, and it distinguishes immediate vs. scheduled usage in the first sentence. It stops short of explicit exclusions or naming a sibling (e.g., cancel-campaign to stop a send).

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