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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description stays consistent while adding real operational context: a 100 KB per-page cap with next_offset pagination, a 7-day retention window (DEC-176), and zero cost. It also flags that returned row values and generated outputs are customer data rather than instructions, which is useful trust-boundary information for an agent that will ingest this text. Minor gap: no note on whether the export itself is synchronous for large runs.

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 core action and output shape, then conditions, then retention and cost. Sentences are short and each carries information; "Free ($0)" is slightly redundant phrasing, and the prompt-injection caveat, while valuable, reads as bolted on rather than integrated.

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 does the work of explaining the return payload: named columns for CSV, a JSON array for the other format, and a paged envelope with next_offset. Combined with the when-to-use trigger and retention window, an agent has enough to call it correctly; only the exact JSON envelope shape remains unstated.

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 100%, so all four parameters are already documented in the schema, which sets the baseline at 3. The description adds only indirect parameter meaning — the 100 KB page cap that motivates next_offset/offset values — and does not clarify the relationship between the request's offset field and the returned next_offset.

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 description names a specific verb and resource ("Export processed rows from a run") and enumerates the exported columns (row,status,output,error_code) plus the two formats, so the agent knows exactly what it produces. It never names the closely-named sibling get_run_rows, so the boundary between reading rows in-app versus exporting them is left for the agent to infer.

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 gives a concrete triggering condition: use it when a Google Sheet run hit sheet_too_large or has unwritten rows. That is actionable context rather than a generic blurb, but there are no explicit exclusions or named alternatives (e.g. get_run_rows for small reads), so the agent must reason about the cutoff itself.

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