Plan a carousel

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

With readOnlyHint=true and openWorldHint=true already covering the safety profile, the description adds the genuinely useful context: this is a planning/generation step, capped at 20 slides, and it is not the publishing action itself. Since there is no output schema, stating that the result contains slides plus caption and hashtags fills a real gap; it does not say whether model selection (set_ai_models) affects output quality.

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?

Two sentences, front-loaded with the input-to-output transformation, then the downstream step. No filler, no restatement of the title, and every clause carries information an agent needs to select or chain the tool.

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 read-only generation tool with five optional parameters and no output schema, the description covers purpose, output shape and the follow-up call. The remaining gap is minor but real: the semantics of audience and template are left entirely to an undocumented schema.

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 only 20% (source_path is the lone documented field), so the description carries more burden than usual. It usefully implies the text/source duality and the 20-slide ceiling, but audience and template are never explained—an agent cannot tell whether template refers to a name from list_templates or free-form layout guidance, and the default of 8 slides is only in 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 transformation (text/article/notes/transcript -> carousel outline) and enumerates the concrete artifacts produced: slide-by-slide headline, body, visual, caption and hashtags. It also names the sibling it hands off to, publish_carousel, so an agent can separate planning from publishing without opening either 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?

Gives an explicit workflow position: generate the outline here, design slides from it, then publish with publish_carousel. That is clear when-to-use guidance relative to the publishing sibling, though it offers no exclusions (e.g., when to prefer content_ideas or generate_caption instead) and no prerequisites such as whether an account must be connected.

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