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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds behavioral value by disclosing that polling may return partial outputs and includes measured media metadata and credit state, which is information beyond the annotations.

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?

The description is a single efficient sentence that front-loads the verb and object and includes only substantive details. There is no redundant restatement of the title or schema.

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 one-parameter polling tool with an output schema and safety annotations, the description is largely complete: it states what is polled, what the response includes, and the ownership constraint. Explicitly saying the task_id comes from generate_video would be helpful but is easily inferred from the sibling tool list.

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?

The schema only provides task_id with a uuid format and no description, so coverage is 0%. The description compensates by clarifying that the task is an owned source-video task, giving the parameter meaningful context and an ownership constraint beyond the bare 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?

The description uses the specific verb 'Poll' and identifies the resource as an 'owned source-video task', with concrete response aspects: partial outputs, measured media metadata, and credit state. This clearly differentiates it from siblings like generate_video, cancel_video_generation, and quote_video_generation.

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 clear context: use this to poll a source-video task the caller owns, which is distinct from creating, canceling, or quoting. It does not explicitly name an alternative, but the ownership and source-video constraints provide clear situational guidance.

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