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

The description goes well beyond the annotations, disclosing that media_id must be a bare id from a previous generate_video* result, that the job is pinned to a specific Google account's project, and that unknown ids produce a clear error rather than a mysterious failure. It also adds cost/credit details, the default model, and the 8-second extension length.

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 well-structured and front-loaded: purpose first, then the most critical constraint (media_id), then usage guidance, then pricing/default model, then project_id. Every sentence adds necessary context; there is no filler or 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 complex 6-parameter tool with no output schema, the description covers the subtle and non-obvious areas agents would most likely get wrong: bare media_id format, account pinning, invalid id behavior, and optional project_id semantics. The remaining parameters (aspect, include_preview) are self-explanatory or adequately covered by schema defaults.

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 input schema has zero property descriptions, so the description carries the full burden here. It thoroughly explains media_id and project_id, including subtle behaviors like account pinning and error handling, and names the default video_model_key with credits. However, prompt, aspect, and include_preview receive no dedicated explanation, leaving some minor gaps in an otherwise strong effort.

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 opens with a specific verb and resource: 'Continue a video this service already generated.' This clearly distinguishes it from siblings like generate_video and edit_video by focusing on extending an existing output rather than creating or modifying from scratch.

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?

It explicitly states when to use the tool: 'Use for shots that need to run longer than one generation, or to keep a scene going without re-describing it.' It also contrasts with the alternative, a fresh text-to-video call, explaining why this tool is the right choice when continuation should inherit the source clip's world.

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