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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds genuinely new consequences: in-flight contacts stop receiving messages, and the operation cannot be undone. That is exactly the behavioral context an agent needs before a destructive call.

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?

Three short sentences, front-loaded with the destructive nature, then the side effect, then the escape hatch. Every sentence carries distinct information and none is wasted.

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, two-required-param tool with full schema coverage and annotations, the description covers permanence, side effects on active contacts, and the non-destructive alternative. No output schema exists, and none is needed here.

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% — site_id, journey_id, and user_goal are all documented in the schema with starter hints (list_sites, list_journeys). The description adds no parameter-level detail beyond that, so the 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?

States a specific verb and resource ('Permanently delete a journey') with the permanence qualifier up front, which cleanly separates it from siblings like rename_journey, set_journey_enabled, or remove_journey_step.

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?

Explicitly names the alternative for the most likely confusable intent: 'to pause one, use set_journey_enabled with enabled false.' That is a concrete when-not-use rule with the sibling and argument spelled out, leaving nothing to infer.

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