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

Beyond the annotations it discloses the async execution model, the side effects (pack saved to Puley history, email sent), and the cost profile (~$1 drawn from the balance, subject to a daily limit) — exactly the context annotations cannot convey. One minor tension: the description implies repeat calls return the existing run rather than re-executing, which sits awkwardly with idempotentHint=false, but it is a clarification rather than a contradiction.

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?

Front-loaded with the execution mode and packed into one dense paragraph where nearly every clause adds a distinct fact (inputs, output, persistence, cost). A few phrasings such as "works out why they work" are loose, but nothing is 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 multi-step, side-effecting tool with no output schema, the description covers what is returned (progress or finished pack), where it lands, and what it costs. It omits expected duration and what the pack contains, which would help an agent set expectations, but nothing essential for a correct call 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 coverage is 0%, so the description must carry the load and largely does: it explains "model" as the video model with a low-cost default, and its phrasing "in a niche on platform tiktok, instagram or youtube" effectively enumerates the valid platform values that the schema leaves as a bare string. It does not address the schema's empty-string default for model, which conflicts slightly with the stated low-cost default.

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?

"Finds this week's most-watched videos in a niche on platform tiktok, instagram or youtube, works out why they work, writes an original video, records the voice-over and makes the clip, saves the pack ... and emails it" names the exact verb chain and artifact produced. An agent can distinguish this from find_videos (a search) or make_media (a single render) without opening any schema.

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?

"Runs once, in the background" and "the same request again returns its progress or the finished pack" give concrete calling and polling guidance, which is the key operational question for this tool. It stops short of naming alternatives (find_videos, search_trends, make_media) or stating when to prefer them, so no explicit when-not guidance.

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