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

Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds meaningful context beyond that: it explains the possible job states, including approval_required (waiting for a person) and failed (with any refund), and notes that complete jobs include media links and continuing ids. It does not cover rate limits or auth, but the annotations already carry the safety profile.

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 dense sentence front-loads the core purpose and efficiently packs the state list and polling instruction. No sentence is wasted, and the most important operational cue (polling cadence) is included without burying the lede.

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 full burden of explaining return values and does so: statuses, media links, ids for follow-up work, and refund on failure. For a single-parameter getter with clear annotations, nothing an agent needs to call it correctly 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 schema itself documents that job_id is 'returned by a create tool.' The description reinforces that this works with 'any job a tool started' but adds no format, syntax, or constraint details beyond the schema. Baseline 3 is appropriate.

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 and resource ('Status and results of any job a tool started') and enumerates the exact return states (processing, approval_required, ready, complete, failed). This lets an agent distinguish it from creation siblings like create_video or remake_start without opening the schema.

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 to poll every 15-30 seconds until the job settles, which is the critical usage pattern for an asynchronous job-status tool. It lacks an explicit when-not or named alternative, but no sibling serves the same polling purpose, so the guidance is effectively complete.

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