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

Annotations cover the safety profile (destructive=true, non-idempotent, openWorld), and the description adds material context beyond them: the async job pattern with a get_job polling loop and the credit cost (50 short / 80 medium). That cost and the required public URL are exactly the side-effect facts an agent needs before spending credits.

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?

Three tight clauses, front-loaded with the core purpose, then async behavior, then cost/prerequisite. No filler; every sentence carries needed information.

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?

With no output schema, the description correctly discloses the return shape (jobId, poll via get_job) and the credit cost. Remaining gaps are minor — it doesn't say what the finished artifact is (a video) or clarify the platform enum's effect, but it is sufficient to invoke the tool correctly.

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 71%, so most parameters are already documented (prompt, duration, styleTemplateId, referenceImageUrl, styleReferenceImageUrl). The description reinforces referenceImageUrl must be public and ties 'short'/'medium' to scene counts, but adds little for the undocumented platform and name fields. Baseline 3 is appropriate.

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 and resource: 'Generate a dialogue-first short drama from a single reference image', with concrete scope (5-scene short / 9-scene medium). This is distinctive against generic siblings like create_video or seedance_generate_video, but it never names an alternative, so the differentiation is inferable rather than explicit.

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 gives operational context — 'ASYNC — returns a jobId; poll get_job until completed' and 'Requires a public referenceImageUrl' — which implies usage. However, it gives no when-to-use guidance against the many other creation tools (create_video, create_ai_edit, seedance_generate_video), leaving the agent to guess which generator to pick.

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