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

Annotations already flag readOnly/unmodified behavior, but the description adds valuable behavioral context: per-row failures do not block other rows, finished outputs remain downloadable for 7 days, and the response names the REST endpoint. These details go beyond what annotations alone convey.

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?

The description is a single well-structured sentence that front-loads the core purpose and then packs in key details (attempt count, summary, failures, retention) without redundancy. No fluff or repetition of the title.

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?

Given the simple one-parameter input and lack of an output schema, the description fully covers what the response contains, how failures are handled, and the retention rule. An agent has everything needed to invoke and interpret this tool correctly.

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% and the only parameter job_id already has a clear description ('Job id from bulk_submit'). The tool description does not add further parameter-specific semantics, so the baseline score of 3 applies.

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 the exact resource ('one bulk job you own') and the specific information returned: state, attempt count, summary, produced count, and per-row failures. It directly distinguishes from sibling tools like bulk_list (multiple jobs) and bulk_submit (creating jobs) by using 'one' and 'you own'.

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 context is clear: use this for a single job you've submitted (job_id comes from bulk_submit) after it runs. It implicitly contrasts with bulk_list for listing all jobs. However, it does not explicitly name alternative tools or provide when-not-to-use guidance.

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