Start a silent-lead rescue

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds value beyond them: required OAuth scopes (luca:queue_ops), data sensitivity (redacted), the Idempotency-Key requirement and server-generated fallback, and the confirm:true gate. It could still say what the rescue cadence actually sends or how failures surface, but this is solid added context.

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?

The behavioral core is front-loaded in two efficient sentences. The trailing metadata block (operation, scopes, idempotency, confirm, workspace) is dense but each line carries operative information, so little 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?

With an output schema present, return values need no explanation, and the description covers scopes, idempotency, confirmation, and workspace scoping for a destructive, nested-body tool. The main remaining gap is routing guidance against the semantically similar rescue/enroll siblings.

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 80%, so the schema largely documents confirm, idempotencyKey, workspaceId/Slug and leadIds. The description adds genuine meaning only for workspaceId/workspaceSlug ('override the default workspace configured by environment') and repeat the confirm/idempotency notes; it says nothing about cadenceTemplate's light/standard/aggressive options. Baseline 3 fits.

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 ('Enroll silent leads into the multi-day rescue cadence') and clarifies the real-world effect ('Starts outbound touches to real leads'). It does not distinguish itself from plausible siblings such as luca_rescue_silent_leads or luca_campaigns_enroll, so it stops just short of full clarity.

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?

There is no when-to-use guidance versus alternatives. Given near-duplicate siblings (luca_rescue_silent_leads, luca_campaigns_enroll) and no explanation of which cadenceTemplate to pick, the agent is left to infer selection.

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