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

Annotations already declare a safe read-only, closed-world operation, so the bar is lower. The description still adds real behavior: a hard 50-row preview cap, offset-based pagination, and the existence of a CSV URL for the full export rather than truncated rows.

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 dense sentence that front-loads the preview semantics and appends the secondary details (count, CSV URL). Every clause carries information, though the '+' concatenation style is slightly compressed.

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 describing the return payload (rows, total count, CSV export URL). Only the failure behavior for an unfinished job is left 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 coverage is 0%, so the description must carry the parameter burden and largely does: it documents the 50-row cap tied to 'limit' and the pagination mechanism tied to 'offset'. job_id is self-evident from the name.

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 ('Preview of a finished job's rows') and clarifies the payload: rows, total count, CSV URL. It implicitly distinguishes from get_job (metadata) and the create_* siblings, though it never names an alternative explicitly.

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?

The phrase 'finished job' implies this should only be called after completion, and 'paginate with offset' tells the agent how to iterate. However, it names no alternative tool and gives no guidance on 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.