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

Beyond the annotations (non-read-only, open-world, non-idempotent), the description discloses the billing model (consumes the clip's seconds from the account's monthly allowance), latency (~50 s wait), and the async job pattern returning a jobid consumed by vids_get_job. Those are the operational facts an agent needs before committing to an expensive, slow, non-idempotent call.

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?

One tight paragraph, front-loaded with the core capability and mode list before cost and job mechanics. It is dense with parentheticals ("(referenceImage_1..3 images and avatar_1..3 voiced avatars)") which slightly hurts scanability, and the trailing "POST /videos" is an implementation detail of marginal value to an 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?

For a 12-parameter, no-output-schema creation tool, the description covers the mode matrix, prompt syntax, cost, latency, and what is returned (a jobid for vids_get_job). Since there is no output schema, that return-value sentence is essential and it is present; the only soft spot is the ambiguous "waits up to ~50 s" failure path.

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 100%, so the schema already documents every parameter and the baseline is 3. The description adds real meaning on top: the @referenceImage_N/@avatar_N prompt marker convention, the fact that avatar lines are written as prompt text, and the grouping of referenceImage_1..3 plus avatar_1..3 into a single mutually-exclusive "references" mode.

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 gives a specific verb and resource ("Generate a 3-15 s clip with sound and speech") and enumerates its three input modes: text-only, a startImage, or up to three references (images and voiced avatars). That makes the capability clear, but it never names the sibling it competes with (vids_create_avatar_video, vids_extend_video, vids_edit_video), so the agent must infer the boundary 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?

It gives concrete how-to guidance: name references as @referenceImage_1 or @avatar_1 in the prompt, and write an avatar's spoken lines into the prompt, plus the mode structure (startImage XOR references). What is missing is any exclusion or alternative routing — nothing tells the agent when to pick this over vids_create_avatar_video or vids_extend_video.

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