generate_carousel

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=false and destructiveHint=false. The description adds genuine value by clarifying that this stage produces text only, preventing the agent from expecting images, but it does not disclose that each call is non-idempotent and will yield different slides, whether any draft is persisted server-side, or any cost/latency profile for the generation step.

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, both earning their place, with the text-vs-image boundary front-loaded and the handoff to render_carousel placed second. No filler or restatement of the tool name.

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 five-parameter generator with a fully documented schema and no output schema, the description covers purpose, scope, and pipeline position adequately. It could do slightly more on what the returned slide text looks like (count relative to maxSlides, structure) and whether state is persisted between this call and render_carousel.

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 100% with per-parameter descriptions, defaults, ranges and two enums, so the schema already carries parameter meaning. The description adds no parameter-level detail at all — nothing on how style and platform interact, or what brandColors influences at the text stage versus the render stage. Baseline 3 applies.

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 states a specific verb and resource — 'Generate carousel slide TEXT (title/content/quote/CTA) from long-form content' — and immediately scopes it against the sibling that produces images. An agent can distinguish generate_carousel from render_carousel 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?

It gives a clear usage context (decompose long-form content) and an explicit next-step routing: 'Then call render_carousel to turn the slides into branded PNG images.' What's missing is any exclusion — nothing says when NOT to use it (e.g. vs. repurpose_content, or short-form sources) or what to do if the returned text is unsuitable.

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