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

The description tags the tool as '[read, AI]', yet annotations declare readOnlyHint=false and destructiveHint=true — a direct conflict in the safety signal an agent relies on. The description also never explains what the destructive flag could mean (credit spend, provider call cost, side effects), leaving the annotation unexplained and contradicted.

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?

It is a dense, front-loaded single block: output shape first, then parameter shapes, then the next-step call. It earns most of its length, though the '[read, AI]' tag and terse brace notation border on cryptic and the safety tag is actively misleading.

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 no output schema, the description usefully inlines the return shape (concepts array of title/story) and the nested brand/ai structures, which is a lot of coverage. It is still incomplete for a 5-parameter AI-backed tool: idea/count/language semantics are absent, and the destructiveHint=true annotation is neither explained nor reconciled.

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 description coverage is 0%, so the description carries the full documentation burden. It does document the two hardest parameters well — brand = {name (required), offer?, description?} and ai = {provider (openai|claude|gemini|xai|llama), account_uuid, model?}, including the omit-for-local-AI fallback — but idea, count, and language are never mentioned, leaving three of five parameters undocumented.

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 definition states what is produced (several promotion video ideas for a shop, generated by a chosen AI account) and exposes the output shape (data.concepts = [{title, story}]), so an agent can tell this is a concept-generation step rather than a render step. It also routes forward to promo_video_scenes. It does not contrast itself with the nearby sibling promo_video_suggestions, which keeps it short of a 5.

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 workflow hint 'Pick one, then call promo_video_scenes' plus 'omit for the local Seliee AI' gives real sequencing and default-selection guidance. However, there is no statement of when to use this versus promo_video_suggestions or create_promo_video, and no precondition for the required brand object beyond its shape.

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