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

Useful behavior beyond the annotations is disclosed: no source quota is consumed and capacity/duplicate estimates are unverified until bytes arrive. Against that, the batch-of-20, receipt-keeping and retry guidance describes a transfer step rather than this call, and sits awkwardly next to readOnlyHint=false for something framed as a 'preview'.

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 first sentence is well front-loaded, but the remaining three sentences cram in guidance for multiple workflow steps (batching, receipts, retries, pending imports) that is only partly relevant to a preview call. The result is diffuse rather than tight, and an agent must untangle which rules apply here.

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 no output schema, the description should carry the return-value burden, and it only hints that the preview surfaces capacity/duplicate estimates. Combined with a complex nested manifest and an idempotencyKey on what is framed as a lightweight preview, the picture is incomplete for an agent to call it confidently.

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 67%, with projectId and idempotencyKey already documented in the schema; the description adds no parameter-level meaning at all. The large, nested, enum-heavy manifest object — the actual payload — is left entirely to the schema, so the description neither reveals nor clarifies 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?

The opening sentence gives a specific verb and resource (preview selected files) and scopes it as free/no-quota, which separates it somewhat from helvabase_upload_sources. However, the following sentences describe transferring batches, retrying failed files and inspecting pending imports — actions that belong to other tools — leaving it ambiguous whether this tool previews or also uploads.

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?

It implies usage (preview before spending quota, review the exact selection with the user), which is usable sequencing context. But it never names the alternative it hands off to (upload_sources, source_imports, reconcile_source_import) and offers no explicit when-not-to-use condition.

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