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

Annotations cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context beyond them: blank selected cells can mutate merged data, acceptance and visibility remain unverified, no documents are fetched, and nothing is submitted to Google. It also discloses concrete limits (1 MB request, 10,000 reference IDs).

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-loaded with what is returned, then constraints in short declarative fragments; every sentence carries a distinct caveat or limit. The telegraphic phrasing is dense but not padded, so nothing reads as 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?

With no output schema, the description still conveys the return artifact (a TSV or facts CSV built from chosen columns), the merge/no-mutation guarantees, and the unverified acceptance status. It stops short of describing the output column layout, but otherwise covers what an agent needs to invoke it safely.

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 csv, columns, reviewed, referenceIds, and the oneOf constraint in detail. The description restates the 1 MB request limit and the 10,000 reference-ID cap and echoes the blank-cell merge caveat, adding little beyond what structured fields provide.

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: returns a real TSV for 1-5 merchant-authored products or a facts CSV, scoped by review and chosen columns. An agent can tell what it produces, though it never names or contrasts with the sibling validate_answer_feed, so 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?

"After explicit human review and chosen columns" gives a clear precondition for calling it, and "Never drops products, creates facts or submits to Google. No documents are fetched" sets firm negative boundaries. No alternative tool or when-not-to-use condition is named, so it stops short of full routing guidance.

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