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

Adds real context beyond the annotations: no run record is created, no quota is consumed, and it requires the explicit test-delivery configuration to be enabled. It does not disclose that a real external email is sent via Resend (consistent with openWorldHint=true) or what happens on failure.

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 tight sentences, with the distinguishing behavioral guarantees front-loaded right after the action. No filler.

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?

With six parameters, an enum, and no output schema, the description leaves open which automation is used, what the response contains, and what the undefined 'explicit test-delivery configuration' refers to. Adequate for a simple send, but an agent still has gaps before invoking.

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 83%, so the schema already documents almost every parameter (uid, bearer_token, conversation_id, preferences_mode, agent_preferences). The description mentions none of them and never explains how automation_id selects which sample is delivered, so it adds no parameter-level value.

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 concrete verb and resource ('Send the fixed-sample branded lead-automation email directly through Resend'), which separates it from run_automation_now and retry_automation_delivery. What the 'fixed-sample' content actually is (and whether the caller can influence it) stays ambiguous.

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?

'This creates no run and consumes no quota' clearly signals the pre-flight/test use case versus real execution siblings. It stops short of naming run_automation_now or retry_automation_delivery as the alternatives for an actual send.

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