Generate the video (spends credits)

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

It discloses the credit charge timing, automatic refund on failure, queued return behavior, and insufficient-balance handling. These behaviors go well beyond the annotations (`readOnlyHint: false`) and tell the agent exactly what side effects to expect.

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 longer than average but the content is almost entirely operational guidance needed for a credit-spending tool. It is front-loaded with the most critical warning, though some repetition with the title ('spends credits') and a few overlapping consent instructions add slight redundancy.

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?

Without an output schema, the description explains what the call returns (`video_request_id`), how to follow up (`get_video`, 20-30s polling until `done`), and what to give the user (`output_url`, `share_url`). It also covers the insufficient-funds path, making the expected behavior 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?

The only parameter `product_id` has a schema description that already covers its meaning completely, so the tool description adds no new semantic information. The baseline of 3 applies because schema coverage is 100%.

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 'Render the video' and identifies the exact resource (`product_id`), so the agent knows this is the rendering action. It also separates it from siblings like `get_video` and `update_video_direction` by noting the product's current direction/settings are used as-is.

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 explicitly requires user approval and cost disclosure before every call, and it lists forbidden uses ('see what happens', retry in progress, self-initiated batch). It also tells the agent to poll `get_video` afterwards, giving a clear and complete workflow.

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