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

With only minimal boolean annotations, the description carries the behavioral burden. It discloses that multiple items run in parallel, caps batches at 10, and states that the tool returns an audio URL and word-level captions. It does not mention caching, cost, or why idempotentHint=false matters, but the key runtime behaviors are exposed.

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 logically organized: purpose, use cases, voice guidance, tone guidance, batching behavior. It is efficient and mostly free of filler. There is minor redundancy with the schema's voice description, which also states the no-mixing-voices rule, but the prose is compact and every section contributes actionable information.

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 generation tool with an output schema, the description covers when to use it, how to set tone and voice, and how batching works. It also tells the agent what the response contains. It could briefly mention what to do after generation, such as attaching the returned audio to a node, but the essentials needed to call and use the tool are present.

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?

The input schema already documents all parameters, so the baseline is high. The description adds meaningful guidance beyond the schema, such as matching voices to topic and audience, giving concrete tone examples for quizzes/surveys/personality quizzes, and reinforcing the no-mixing-voices rule. This is a clear value-add over the structured field descriptions.

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 opens with a clear verb and resource: 'Generate narration audio from text with word-level captions.' It then names concrete use cases—quiz narration, survey introductions, form instructions—which makes the purpose unmistakable and separates it from sibling tools like clipform_generate_video or clipform_search_music.

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 description explicitly tells the agent when to use the tool and even instructs proactive suggestion for quizzes and content-rich forms. It also provides a strong voice-consistency rule ('reuse that SAME voice... Never mix voices'). However, it does not explicitly contrast with alternative tools or state when not to use it, so it stops short of full guidance.

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