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

The description goes beyond the annotations by disclosing that execution is asynchronous, that a generation_id is returned, and that polling get_generation is required. It also adds cost information ($0.05 per video), which is useful operational context not present in the schema or annotations. There is no contradiction with the 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 remarkably compact: two sentences with zero filler. It front-loads the core purpose, then immediately supplies cost and async behavior. Every sentence earns its place and adds actionable 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?

Given that there is no output schema, the description correctly explains the return value (generation_id) and the required follow-up action. It covers the essential workflow an agent needs to invoke and monitor the tool. It does not address edge cases like invalid videos, but for typical usage this is sufficient.

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 100%, so the schema fully documents both 'video' and 'prompt.' The description does not add extra parameter-level semantics, but it doesn't need to; the baseline of 3 is appropriate when the schema carries the load.

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: 'Add sound to silent videos.' This clearly distinguishes the tool from audio-generation siblings like ai_sound_effects or ai_music_generator by emphasizing that the input is a silent video. The purpose is immediately understandable and not a tautology of the name.

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 provides a clear usage context: it applies to silent videos, and it explains the asynchronous workflow of calling get_generation until 'completed.' It does not explicitly name alternative tools or state when not to use it, but the context is clear enough for an agent to identify the appropriate scenario.

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