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

Annotations only declare non-read-only and open-world; the description adds the substantive behavior an agent needs: an email round-trip with a code the user must supply, an async ~5 minute build, a returned id plus a watchable page, and a completion email to the user. That is exactly the context annotations cannot convey.

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-loads what the tool produces, then walks the call sequence in order, then closes with the follow-up tool and the timing caveat. Four dense sentences with no filler or repetition of schema text.

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?

No output schema exists, and the description compensates by naming what comes back (an id and a page to watch) and how completion is signaled. Combined with the timing and follow-up guidance, an agent can drive the whole flow correctly.

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 baseline is 3; the description adds ordering semantics the schema only implies — url and email on the first call, then url, email and code on the second. It does not mention the optional `instructions` parameter, leaving that entirely to the schema.

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 artifact ("Build a 15-second video ad kit") plus the input source (a business's web page), with concrete examples of what pages qualify. This is immediately distinguishable from the sibling get_ad, which only retrieves a finished ad.

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?

Explicitly describes the required two-call sequence and the condition separating them (email verification), and routes the agent onward: "follow it with get_ad" once the ~5 minute build completes. Nothing about when or how to invoke it is left to inference.

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