caption_video

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

With no annotations, the description carries the full burden. It discloses job duration (3-8 minutes), that the user will receive an email, and that the agent can check status. This adds valuable behavioral context beyond the schema.

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 concise and well-structured: the first sentence states the core purpose, followed by actionable guidance and behavioral notes. No redundant 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 the tool has 4 parameters, no output schema, and is asynchronous, the description covers purpose, defaults, timing, notification, and a follow-up action (status check). Slightly incomplete on return value, but acceptable.

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 0%, so the description must compensate. It explains defaults for aspect_ratio ('9:16') and caption_style ('minimalist'), but does not describe video_url or caption_color. Thus partial value added.

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 clearly states the tool's purpose: 'Add captions to a short video (up to 5 minutes).' It uses a specific verb and resource, and distinguishes from sibling tools like clip_video and get_clip_status.

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 guidance on when to ask the user for parameters (aspect_ratio, caption_style) and defaults if unspecified. It also mentions the async nature and suggests checking status via get_clip_status. However, it does not explicitly state when not to use this tool.

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