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

Annotations declare the safety profile (not read-only, not destructive, not idempotent), and the description adds genuinely non-schema behavior: output is silent for dubbing, it is free but consumes storage, and the result must be retrieved via get_generation. The async/polling requirement is the most valuable disclosure here.

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?

Four short sentences, front-loaded with the core transformation, followed by mode, output characteristics, cost, and the async retrieval hint. No filler and no repetition of the title.

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 3-parameter generation tool with an output schema, the description covers inputs, output nature (silent), cost, and retrieval path. Nothing an agent needs in order to invoke this correctly is missing.

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 0%, so the description must carry all parameter meaning, and it does: sources = 1–3 owned 1–15 second takes, duration_seconds = target duration up to 30 minutes, mode = loop or ping-pong. All three parameters, including the enum, are explained in prose.

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?

States a specific verb+resource (rotate/loop video takes to a target duration) with exact scope constraints (1–3 owned takes of 1–15s, target up to 30 min). An agent can immediately distinguish this from join_clips or trim_video, which manipulate footage differently.

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?

Gives the operative context that this is an asynchronous job and that get_generation is how you wait for it, plus the ownership/duration preconditions. It stops short of naming siblings it competes with (e.g. join_clips) or an explicit when-not-to-use, so it is clear but not fully routing.

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