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

Annotations only mark it as a non-idempotent, open-world write; the description adds the operationally critical behaviors: it is asynchronous (returns a Job ID, media produced in background), credits are consumed per second at quality/resolution-dependent rates, impossible quality/silence combinations are silently upgraded and charged at the higher tier, and silent video is irreversible. That is far beyond what annotations convey.

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 three modes and dense with useful rules, but the credit costs are restated three times (per-second rates, then worked examples), and the quality guidance duplicates the schema's own quality description. Slightly long, though nearly every sentence earns its place.

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 9-parameter async generation tool with no output schema, the description supplies the missing return handoff (Job ID, then wait_for_jobs -> Asset ID for patch_film), cost estimation duties, failure handling, and mode selection. An agent has everything needed to invoke and follow up 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?

With 67% schema coverage, the description meaningfully compensates: it explains quality tier semantics and auto-upgrade behavior, generateAudio's null/true/false meaning plus the irreversibility caveat, the references string formats and ordering rules, and the standard defaults for duration, aspect ratio, resolution and audio. Resolution, duration and aspectRatio are left to their schema enums/bounds, which is adequate.

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 first sentence states a specific verb and resource and enumerates the three distinct generation modes (from prompt, animate an image via referenceAssetId, and compose from up to 5 references). It clearly distinguishes itself from siblings like generate_image and generate_music by naming the medium and its inputs.

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?

Gives explicit when-to-use rules: the load builtin-generative-video prerequisite, quality selection guidance (standard for B-roll, high for hero shots, highest only on request), when to use references vs referenceAssetId, and when generateAudio may be false. It also prescribes the downstream workflow (wait_for_jobs then patch_film) and the retry policy after a credit refusal.

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