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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds substantive behavior: the result URL is expiring, eta is derived from media length times rolling per-step averages, and burn progress is real ffmpeg progress. These are things an agent cannot infer from the annotations or schema and directly affect how it should poll and consume results.

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?

Front-loaded with the core action, and every clause in the long enumeration conveys distinct, useful information about a returned field. It is a dense run-on list rather than cleanly structured prose, but 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?

With no output schema and only one input param, the description carries responsibility for explaining what comes back, and it does so field-by-field (step enum values, progress scale, eta sources, cost, expiring URL). Combined with the resume_job handoff for failed jobs, an agent has enough to call it and interpret results 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?

There is a single parameter with 100% schema description coverage ('Job id returned by transcribe or burn_captions'), so the schema already carries the semantics. The description adds nothing about jobId itself, which is the baseline case for a high-coverage single-param schema.

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?

Opens with a specific verb+resource ('Read any job') and immediately scopes it as a single-job lookup by id, which implicitly separates it from the batch-oriented list_jobs sibling. It doesn't name list_jobs explicitly, so the differentiation is implied rather than stated.

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?

Gives real operational guidance: 'pollAfterSeconds (wait that long before the next poll)' tells the agent how to poll, and 'A failed caption job with resumable:true can be restarted with resume_job' names a sibling and the exact condition for switching to it. It lacks an explicit statement of when to use list_jobs instead, 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.