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

Annotations already provide readOnly, idempotent, and non-destructive hints, and the description adds valuable behavior: the exact response envelope, terminal statuses, and the shape of successful output. This gives the agent a clear polling contract beyond the annotations.

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 reasonably compact, front-loaded with the core action, and every sentence adds useful guidance: origin, return shape, polling condition, and read-only caveat. Nothing is wasted.

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?

For a one-parameter polling tool with an output schema and strong annotations, this description is complete. The polling loop, terminal states, output expectations, and boundary against job creation are all covered.

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% for the single `jobId` parameter, so the schema already carries the semantic weight. The description's reference to `jobId` adds no real meaning beyond what the schema says; it simply reinforces that the id comes from the submit call.

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 action ('Fetch') on a specific resource (Oxylabs LLM job) and ties it to the submitting sibling, `post_oxylabs_llm`. It also distinguishes itself from job creation by explicitly saying it 'cannot start one.'

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?

Explicitly tells the agent when to repeat calls ('until status is completed, failed, or cancelled') and what success looks like. It also names the submitting tool and clarifies this is a read-only polling operation, which distinguishes it from starting or cancelling jobs.

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