Preview a lead import

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

Goes well beyond the annotations by disclosing the underlying operation (POST /api/leads/imports/preview), required scopes (leads:read, luca:draft), data sensitivity (full_content), and that idempotency is not required. The one unresolved behavioral point is whether a "preview" persists anything, which matters because readOnlyHint is false; that ambiguity keeps it from 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?

Purpose is front-loaded in one sentence, followed by compact operational metadata lines that each carry distinct information (operation, scopes, sensitivity, idempotency, workspace override). The key-value style is terse but nothing 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 prose, and the description supplies the operational envelope an agent needs: auth scopes, sensitivity, idempotency stance, and workspace targeting. The remaining gap is that it never clarifies the dry-run nature of a preview against a non-readOnly annotation.

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?

The only parameter mention is the workspaceId/workspaceSlug override, which merely restates the schema's own descriptions. The bulk of the surface – rows, mapping.identity, consents, identities, customFields, tagsDelimiter – is documented only by the schema (coverage 67% on a deeply nested body), and the description adds no semantics for any of it.

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 plus resource (preview a mapped CSV lead import) and its position in the workflow ("before applying it"), which implicitly separates it from the sibling luca_leads_import_apply. An agent can tell what this does and which sibling follows it without opening either schema.

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?

"before applying it" gives clear sequencing context for when to call this tool relative to the apply step. It does not name alternatives explicitly or state exclusions, but the usage context is unambiguous enough for an agent to place it correctly in the import flow.

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