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

The description is transparent about key behaviors: it creates a new project, spends credits, returns a job id, and exposes live progress via job.output. It also explains downstream side effects (seeding characters, locations, episodes, shots, segments), going well beyond the sparse annotations.

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 concise yet dense with essential information. Each sentence serves a purpose: core action, creation semantics, async progress, downstream effects, cost, and polling guidance. No filler or redundancy.

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?

Given the tool's complexity—async job handling, credit costs, project creation, and seeding of related entities—the description covers all the critical operational context. It tells the agent what to expect, how to monitor progress, and what downstream tools can then be used.

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?

All 9 parameters already have clear schema descriptions, including the important idempotency_key semantics. The tool description adds helpful context by clarifying that no project_id is accepted and that the job is asynchronous, which complements the schema without repeating every field.

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 action ('Write a full multi-episode script from a story premise') and clearly distinguishes this tool from siblings by noting it creates a new project rather than editing an existing one. It also clarifies that it returns a job id, which separates it from direct-return tools.

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 says this tool does not edit an existing project and takes no project_id, which helps an agent choose it for new-project creation. It also mentions spending credits and polling with get_job, giving practical guidance on how to handle the asynchronous workflow.

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