Preview a broadcast

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), and the description adds genuinely useful context beyond them: the required OAuth scope, 'data sensitivity: full_content', and the idempotency behavior ('provide idempotencyKey for safe retries, or the server will generate one'). It does not explain what a refresh does to existing preview data, so it is not a 5.

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 purpose sentence is front-loaded, followed by compact operational metadata. Lines are dense (scope/sensitivity packed into one line) but every sentence carries information. 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?

An output schema exists, so return values need not be explained. For a 5-param tool with a nested object, the description covers operation, auth scopes, idempotency, and workspace selection adequately. The only notable omission is any indication of what refreshing the preview changes or produces.

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 60%. The description clarifies idempotencyKey and the workspaceId/workspaceSlug override, which the schema also documents. However, the nested body.sampleSize parameter (the actual preview control, 1-20) is undocumented in both the schema description and the description, leaving a real gap. Baseline 3 for partial compensation.

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?

The description opens with a specific verb+resource: 'Refresh broadcast recipient and sample-message preview,' which is distinct from read siblings like luca_broadcasts_get or luca_broadcasts_list. The operation endpoint (POST /api/broadcasts/{id}/preview) reinforces this. It stops short of explicitly contrasting itself with the get/list siblings, so it lands at 4 rather than 5.

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?

The description gives operational context (required scopes, idempotency requirement, workspace override) but never states when to reach for this tool versus alternatives such as luca_broadcasts_get or luca_broadcasts_approve/launch. Usage is only implied by the 'refresh preview' framing, which is the definition of a 3.

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