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

Goes well beyond the annotations by disclosing cost (10 credits, adds 8 seconds), the default model, the account-pinning behavior ('the job is pinned to that account instead of rotating'), and the failure mode for an unrecognized id ('a clear error, not a mystery failure'). Annotations only give the generic mutation/open-world profile; the description adds real operational context.

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?

Front-loaded with the purpose and organized into labeled paragraphs per parameter, so an agent can scan it. A few phrases are slightly embellished ('not a mystery failure') but nothing is truly wasted; it is a touch longer than strictly necessary.

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?

No output schema exists, so the description must cover returns, and it discloses the cost/added-duration and error behavior instead. Combined with annotations covering the safety profile, the main gap is that four schema parameters (seed, aspect, include_preview, alternate model keys) get no descriptive treatment.

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?

With 0% schema coverage the description must carry parameter meaning, and it does for the critical ones: media_id is explained down to the format gotcha ('the bare id, not the /v1/media/... path') and project_id is explained with an omit-if-unsure default. It also names the default video_model_key and its credit cost, though seed, aspect, and include_preview are left entirely to 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?

States a specific verb+resource: 'Continue a video this service already generated — Flow writes what happens next.' This clearly distinguishes it from generate_video (fresh generation), edit_video, and recast_video, all of which are siblings with overlapping surface area.

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 states when to use it ('shots that need to run longer than one generation, or to keep a scene going without re-describing it') and contrasts it against the alternative ('a fresh text-to-video call cannot do' this). It also states the prerequisite constraint: only videos made through this service can be extended.

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