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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the response array matches the request order, that the API only creates presigned URLs rather than uploading, and that callers must later send a PUT request. It also includes important edge-case behavior about gif support and hotlinked URLs, giving the agent realistic expectations.

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 long but every section earns its place: purpose, response ordering, extension lists, a special-case note, an upload example, and MCP guidance. It is front-loaded with the core purpose and progressively adds operational detail, making it easy for an agent to extract what it needs.

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 tool with one parameter and an output schema, the description is remarkably complete. It covers when to use the tool, how to construct the request, what happens after receiving URLs, and how to integrate results with create tools. The inclusion of extension constraints and direct-URL caveats addresses likely failure modes without requiring the agent to inspect external documentation.

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?

Although the schema already describes the items parameter at 100% coverage, the description adds substantial meaning: per-asset-type valid extensions, a note that gif is only supported for the face swap API's video_file_path field, and a concrete curl example. This goes well beyond the schema and helps the agent construct valid requests.

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: 'Generates a list of pre-signed upload URLs for the assets required.' It clearly states the tool's narrow role—only for uploading to Magic Hour's storage—and distinguishes it from the many create_* sibling tools by explaining it does not perform generation or upload itself.

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 gives explicit when-to-use guidance: 'This API is only necessary if you want to upload to Magic Hour's storage.' It also explains the intended workflow—upload raw bytes to each returned upload_url outside the generation call, then pass the matching file_path into the create tool—and even cautions against relying on direct public media URLs, directing users to prefer the presigned flow.

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