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

The description labels the tool '[read, AI]', implying a read operation, while annotations declare readOnlyHint=false and destructiveHint=true. This is a direct contradiction about the tool's safety profile. The description also omits any clarification of the destructive behavior or what side effects occur.

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 a single dense sentence with no filler, and the output structure is front-loaded. Every clause carries information, though the run-on semicolon style makes it slightly harder to scan than a structured list would be.

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?

With 7 parameters, no schema descriptions, no output schema, and contradictory annotations, the description is incomplete for confident invocation. It covers the core data flow and output shape but leaves brief, count, and language unexplained and does not resolve the read-versus-destructive conflict.

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?

Despite 0% schema description coverage, the description explains brand fields (name, offer?, description?), concept structure (title, story), source_image, and the ai parameter's relationship to promo_video_concepts. However, brief, count, and language are left undocumented, so it only partially compensates for the schema gap.

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 clearly identifies the result: scenes structured as data.scenes = [{heading, visual, action, narration}] (max 10) for create_promo_video's video_ugc. It distinguishes itself from promo_video_concepts by describing the concept-to-scenes transition rather than the concepts themselves. A specific verb like 'generate' is missing, but the purpose is unambiguous.

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?

It states that concept is required unless source_image is given, and explains that source_image is a product picture the scenes are written from. The reference to promo_video_concepts makes the upstream workflow clear. It does not explicitly name alternatives to avoid, but the conditional prerequisite gives actionable guidance.

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