Apply a lead import

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds value beyond them: required scopes (leads:write, luca:queue_ops), data sensitivity level, the confirm:true gate and rejection behavior, and the idempotency-key fallback where the server generates one. It stops short of describing partial-failure behavior or exactly what side effect the import triggers.

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?

Front-loads the purpose, then lists endpoint, scopes, idempotency, destructive confirmation, and workspace override in compact labeled lines. There is minimal waste, though the scope lines (OAuth scope, data sensitivity) are metadata padding rather than agent-facing guidance.

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, and the description covers auth, idempotency, confirmation, and workspace scoping. The remaining gap is the absence of any pointer to the preview step, which matters for a complex nested mapping payload the agent must build beforehand.

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 80%, so the schema already documents idempotencyKey, confirm, workspaceId and workspaceSlug almost verbatim. The description re-states the workspace override and idempotency semantics but adds nothing about the nested body (rows, mapping, consents, identities), the most complex part of the payload. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource ('Apply a mapped lead import') and pins the exact endpoint (POST /api/leads/imports/apply), so the operation is unambiguous. It does not explicitly contrast itself with the sibling luca_leads_import_preview, which the word 'apply' strongly implies is the prior step, but the differentiation is left to inference.

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?

Provides operational preconditions (requires Idempotency-Key, must pass confirm: true or the call is rejected), which is real guidance for invocation. However it never states when to prefer this over luca_leads_import_preview or what must precede it, so the workflow context is implied rather than spelled out.

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