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

Adds substantial behavior beyond the annotations (which already cover readOnly/idempotent/non-destructive): a hard 50-row cap, cursor pagination, that results may be an interim state while running or aborted, and that calls are free. Also explains that files links are re-signed each call and valid for 30 days, and should be forwarded rather than rows. Lacks only error/empty-result behavior and response field details beyond files.

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 behavior and paging rule, then progressively adds edge-case routing. Dense but every clause carries information; the final paragraph is long but covers distinct failure scenarios that prevent misuse.

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?

No output schema exists, so the description carries the burden of explaining returns, and it does explain segments, ai_column columns, next_cursor, interim states, and files download links. It is nearly complete; only the remaining response fields and the organization/ORG_AMBIGUOUS recovery path are left to the schema.

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 100%, so the schema already documents all four parameters, including the segment values and the ORG_AMBIGUOUS condition for organization. The description adds some semantic framing (kept = actual hits, dropped = discarded with reason, error = not checkable) and explains how next_cursor feeds back into cursor, but does not extend parameter meaning much further.

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 plus scope: it returns the rows of a run, paginated at max 50 per call, with German column names and ai_column extra columns. It is cleanly distinguishable from siblings like get_run_status and run_endpoint/export_run, which are named when they are the better fit.

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 explicit routing rules: pass next_cursor as cursor for the next page; use run_endpoint with tool export_run to get the full file for saving; use export_run with mode raw when a run is failed/cancelled, hangs, or you are debugging. Gives an explicit when-not-to-use (don't hand over rows one by one when finished).

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