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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the mutation and non-idempotency profile is partly pre-supplied. The description still adds real value the annotations do not: this call consumes credits, requires a two-phase cost confirmation, and is asynchronous with a poll-this-other-tool follow-up. It does not, however, describe failure modes, what happens on an unconfirmed cost, or how long generation takes.

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?

Three sentences, front-loaded with purpose, then the credit-confirmation loop, then the return handle and follow-up call. Every clause carries operational information (format source, cost protocol, video id, polling) with no restatement of the tool name or filler.

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 16-parameter, no-output-schema, asynchronous generation tool, the definition covers the essentials an agent needs to call it correctly and handle the response (video id plus get_video polling) and the monetization gate. What is missing is minor parameter guidance for the enum/optional styling fields, which the schema already partially documents.

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?

With 16 parameters and only 44% schema description coverage, the description has to carry weight and it does explain the most consequential ones: format (must come from list_ad_formats), the photo/product_url relationship, product_info, captions, music, and the exact meaning of confirm_credits. Roughly half the params (ratio, duration, engine, language, music_mood, caption_style, caption_position, caption_highlight, logo_image_url) get no mention in the description, so gaps remain that the schema alone does not fully close.

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 and resource ("Starts an Ad Studio video ad") plus its required input (a format id from list_ad_formats) and the 1-5 photo/product-page source material. It is clear on its own, but it never distinguishes itself from the sibling create_video, so an agent choosing between the two has to infer the difference.

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 unusually concrete procedural guidance: call first without confirm_credits to obtain the cost, confirm with the user, then call again with that exact cost, and afterward poll get_video. No exclusions or alternatives (e.g. when to use create_video instead) are listed, which keeps it short of a 5.

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