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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds critical behavioral context: the polling interval, the terminal statuses, the handling of intermediate responses (retry_after_seconds, next_action), and the preference for structured_result. It also includes a concrete GET URL example, fully disclosing the interaction pattern.

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 information-dense but not verbose, delivering purpose, polling guidance, response handling, and an example in three sentences. Each sentence earns its place, and the example is clearly separated for easy scanning.

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 an output schema present, return values are already specified, so the description correctly focuses on the asynchronous polling protocol. It covers when to call, how to poll, what to do while pending, what to do on completion, and the exact endpoint format, making it fully self-contained for correct invocation.

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?

The schema fully documents job_id (100% coverage), so the baseline is 3. The description enhances this by specifying that the job_id comes from deep_research, translate_pdf, or make_slides, and by showing its placement in the URL example, which adds context beyond the schema's generic 'returned when the task was started'.

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 clearly identifies the verb ('Get'), the resource ('the status or result of a job'), and the originating tools (deep_research, translate_pdf, make_slides). This differentiates it from sibling creation tools like make_badge or render_diagram, which are all about generating artifacts rather than checking job status.

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 description provides explicit usage guidance: poll every 15-30 seconds until status is 'done' or 'error', follow retry_after_seconds and next_action while pending, and prefer structured_result when complete. It also indicates the tool is for jobs started by specific tools, which serves as both an inclusion and exclusion criterion.

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