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

Annotations only mark the operation as side-effecting, non-idempotent, and non-destructive. The description adds meaningful behavior beyond that: the job is pinned to the originating farm account instead of rotating, unknown ids produce a clear error, the continuation inherits the source world, and the default model costs 10 credits and adds 8 seconds. None of this appears in the structured 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 front-loaded with the core purpose in the first sentence and each following paragraph earns its place: id provenance, use case, model default/cost, and project placement. It is compact for the amount of critical context it delivers and avoids boilerplate.

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?

The description covers the tricky account pinning, id provenance, project placement, use case, and default model cost. However, with no output schema, it would be stronger if it stated what the call returns (e.g., a job id or media result), so it is not fully complete for an agent that needs to chain results.

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 description coverage is 0%, so the description must compensate. It adds crucial semantics for media_id (bare id only, must come from this service, account-pinned) and project_id (pass the source project or omit it), and it explains the default video_model_key with cost and duration. It does not explain prompt, aspect, or include_preview in detail, but the most non-obvious parameters are well covered.

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 opening sentence names a specific verb and resource: 'Continue a video this service already generated.' It also distinguishes itself from fresh text-to-video by explaining that a continuation inherits the source clip's world, and it ties the subject to a prior generate_video* result, so an agent can tell this from siblings.

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 explicitly states when to use the tool: 'Use this for shots that need to run longer than one generation, or to keep a scene going without re-describing it.' It also contrasts with 'a fresh text-to-video call' and gives concrete guidance about project_id, leaving little ambiguity about selection and call setup.

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