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

Annotations are minimal (readOnly=false, openWorld=true, idempotent=false, destructive=false), so the description needs to disclose behavioral traits. It adds marketing claims ('in just moments', 'captivating') and an input requirement, but does not disclose asynchronous behavior, prompt auto-enhancement, cost implications, or other task-specific behaviors. It does not contradict annotations, but adds little technical transparency.

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 overly verbose with marketing language and ends with a dangling 'Use cases:' header that contains no content. It repeats ideas (turning images into videos) and is not succinct or well-structured for an AI agent.

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 complexity (nested request with two alternatives, polling parameter, output schema), the description is incomplete. It does not mention the two ways to provide an image (URL or file ID), the asynchronous behavior related to polling, or other invocation details. The output schema exists, but the description still fails to provide sufficient context for correct tool usage.

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 50% and the description does not compensate. It mentions 'upload your image' but does not explain the two request variants (src_file_url vs src_file_id), polling, resolution, duration, or negative_prompt. The schema itself describes leaf properties, but the top-level request structure lacks description, and the tool description adds no parameter-level meaning.

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 states it 'transforms text prompts and images into captivating videos', but it does not clearly differentiate this image-to-video tool from the sibling text-to-video tool. The mention of text prompts could mislead an agent into selecting this tool for text-only inputs, and the description does not explicitly scope the tool to image-to-video.

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 some input quality guidance ('photo that features a clean background and a clearly visible portrait'), but it does not provide explicit when-to-use instructions or exclusions relative to alternatives like the text-to-video sibling. Usage is mostly implied by the title and the instruction to start with a photo.

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