read_dv360_report_rows

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

Goes well past the annotations (readOnly/idempotent/openWorld) by disclosing the 1000-record and 10 MiB bounds, that the URL is taken only from Google's authenticated metadata with no arbitrary URL input, that the bounded file is re-downloaded on every call, and that values remain strings to preserve precision.

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 the operation and its limits, and nearly every line adds information. Minor redundancy between 'fetches the report URL only from Google's authenticated metadata' and 'no arbitrary URL input', and the record-composition note sits late.

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 the description is not obligated to describe returns, yet it still explains the state/ready response and that records include headers, totals and footer metadata rather than only performance rows. The main gap is the unexplained max_rows/account parameters for a five-parameter tool.

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 0%, so the description carries the burden, and it only partly does so: query_id/report_id reuse and row_offset continuation are covered implicitly, but max_rows (default 100 vs the stated 1000-record cap) and account are never explained.

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 and resource: reads generated DV360 CSV row values, with concrete scope (up to 1000 raw records, 10 MiB file). This clearly separates it from report-listing or report-metadata siblings, though it never names a sibling outright to route the agent.

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?

Gives real preconditions and continuation rules: it returns state/ready without downloading if the report is not DONE, non-CSV reports are unsupported, and pagination continues via next_row_offset with the same query/report IDs. It stops short of explicitly contrasting with get_dv360_report or get_cm360_report_file.

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