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

No annotations are provided, so the description fully discloses behavior: it polls until terminal state, uses API-suggested interval, has a ~20-second cap per HTTP request, returns timed_out status on incomplete, and does not block indefinitely or over-poll. This is comprehensive for a polling tool.

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?

Two sentences front-load the purpose and termination conditions, followed by detailed mechanics. Every sentence serves a clear role with no redundancy or fluff. Perfectly concise for the information conveyed.

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?

Given no output schema, the description explains the return value for timed-out cases and implies terminal state returns the full video object. It could detail the non-timed-out return structure, but the primary purpose (waiting) is well-covered. A minor gap, but overall complete for its complexity.

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 50% (timeout_seconds described in schema, id not). The description does not explicitly explain 'id' but its role is implied by context ('the same id'). It adds value by stating the default timeout (20) and cap (20) for timeout_seconds, reinforcing schema info. Overall, good compensation for partial schema coverage.

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 states the tool waits for a video to reach a terminal state (completed/failed/preview) and returns it. The verb 'wait' combined with the resource 'video' and explicit terminal states provide precise purpose, distinguishing it from siblings like get_video that likely return immediate 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 gives explicit guidance: poll safely at API-suggested interval, timeout per call, and 'simply call it again with the same id to keep waiting'. It also clarifies what happens on timeout (returns {timed_out: true}), eliminating ambiguity on retry strategy.

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