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

Annotations already establish the safe read profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description only needs to add operational context — and it does: the 50-row per-call cap, offset-based pagination, and the escape hatch of a full-export download URL. It omits error behavior for unfinished or expired jobs, which keeps it out of the top band.

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?

A single sentence that front-loads the primary output (row preview) and then adds the secondary outputs (count, CSV URL) and pagination mechanics. Every clause earns its place and nothing is repeated from structured fields.

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 must describe return values, and it covers all three (rows, total count, CSV URL) plus the pagination contract. The remaining gap is failure/edge behavior — unfinished jobs, expired results, or what the CSV URL's lifetime is.

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 must carry parameter meaning, and it does for two of three params: "max 50 per call" explains limit's practical cap and "paginate with offset" explains how offset is used. job_id is left undefined, though it is self-evident from context.

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 states precisely what is returned — a row preview (capped at 50, offset-paginated), a total count, and a CSV download URL for the full export — which makes it clearly distinct in substance from sibling get_job (job status) and list_jobs. It never names those siblings, so the differentiation is implied rather than explicit.

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?

"a finished job's rows" conveys the precondition that the job must be complete, and the CSV download URL functions as the routing signal for agents that want the full dataset rather than a paginated preview. There is no explicit when-not guidance, e.g. what to do while a job is still running.

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