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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, but the description adds genuine operational behavior: polling cadence, expected latency, the meaning of intermediate statuses, and the indefinite-polling contract. These are traits an agent cannot infer from the annotations alone.

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 and efficient, with the core instruction (poll every 5 seconds) leading. The final two sentences overlap, since 'keep polling indefinitely' and 'do not stop polling after a fixed number of attempts' express the same rule, creating mild redundancy.

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 polling tool with an output schema and rich annotations, the description supplies everything the agent needs: cadence, terminal states, interim states, and duration expectations. Return-value shape is handled by the output schema, so nothing material is missing.

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 single job_id parameter is fully documented in the schema, including the producing tools. The description adds no syntax, format, or sourcing detail beyond the schema, so the baseline 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?

States a specific verb ('poll') and resource ('status of a transcode or convert job'), which scopes it away from unrelated siblings. It does not explicitly address the closely-named sibling get_workflow_status, so an agent must infer the job-vs-workflow boundary.

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 unusually prescriptive usage guidance: call every 5 seconds, treat queued/processing as normal, expect 5–15 minutes for large files, and continue until a terminal status. It explicitly says not to stop after a fixed number of attempts, closing the most common misuse path.

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