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

Beyond the annotations (which only flag non-read-only, open-world, non-idempotent, non-destructive), the description discloses billing behavior ('costs the listed price from the balance; a clip that fails or is refused costs nothing') and the async upload handshake. It doesn't cover polling or how to retrieve the result, which is a minor gap for a job-producing tool.

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 two dense sentences with no filler, and the core purpose and cost model are front-loaded. Slightly packed but every clause carries 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?

For an async, paid generation tool with no output schema, it covers cost, failure charging, and the two start paths. It omits what happens after start_clip (e.g., polling via get_clip), which keeps it just short of fully complete.

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 parameters are already fully documented, including loop, seed, size costs, and content_type usage. The description reinforces image_url's effect (starts immediately) but adds little beyond the schema, so baseline 3 applies.

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 names a specific verb and resource ('turn one still image into a five-second video clip at 24 fps, with sound'), including the model name Phoenix Motion and the output specs. This clearly distinguishes the tool from start_clip, get_clip and list_clips.

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 two concrete invocation paths: pass image_url to start at once, otherwise upload to the returned upload_url and call start_clip. It also points to get_prices for cost. It does not explicitly state when to choose make_clip over start_clip in the upload case, but the branching is clear.

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