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

Annotations already cover read-only, idempotent and non-destructive, so the bar is lower, yet the description adds real context: the four possible states, the three failure reason codes, and the important distinction that a tool error is a call failure rather than a job failure. It stops short of describing the shape of the 'done' summary beyond naming it.

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?

One tightly packed sentence front-loads the core answer and the state enumeration follows in a predictable order, with the error-vs-job-failure caveat last. Nothing is redundant.

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?

There is no output schema, so the description carries the return-value burden, and it does enumerate the states and failure codes. It is nearly complete for a single-parameter polling tool, with only the exact contents of the 'done' summary left vague.

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?

With one parameter and 100% schema coverage the baseline is 3, but the description adds that job_id is the one issued by roof_report_pdf_start and that it can expire or be wrong, which is meaning the regex pattern alone does not convey.

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 names the specific resource (the status of a roof_report_pdf_start job) and its verb is implied by the enumerated lifecycle states. It ties itself explicitly to the sibling that creates the job, so an agent can tell it apart from roof_report_pdf_file without opening the schemas.

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?

It gives a clear usage pattern: call after roof_report_pdf_start, and when the state is rendering, poll again in 10 seconds. It also implies when-not-to-bother, since an unknown state means the job_id is wrong or expired. It does not name the download sibling (roof_report_pdf_file) as the next step after 'done', which keeps it from a 5.

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