create_draft

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

Discloses concrete behavior: dry_run=True writes nothing, false copies media and writes a new project; validation rejects same-track overlaps; experimental font /6 mapping. This adds significant value beyond annotations (readOnly=false, destructive=false). No contradiction with 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?

Compact but information-dense; the description flows logically from purpose to plan fields to clip details and execution behavior, with the main scoping sentence first. Though dense, every sentence earns its place given the complexity.

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 tool with a nested plan object and 0% schema coverage, the description covers all required semantics: field structure, defaults, validation rules, execution modes (dry_run), and behavioral constraints. It is fully sufficient for an agent to build a valid call, and no output schema exists to rely on.

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 has 0% parameter descriptions, so the description must compensate. It thoroughly documents the plan object structure, defaults, clip requirements, coordinate system, and dry_run semantics. Only include_plan is not explained, but its purpose is self-evident from its name.

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?

Description states a specific verb 'Validate/build' and resource 'a new self-contained Mac draft', and explicitly notes it does not register in the native app – a distinguishing trait from siblings like publish_draft or edit_draft. This is far from tautological and clearly identifies the tool's function.

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 gives clear context (for creating a self-contained draft without native registration) and implies use cases from the 'does not register' note, but it does not explicitly compare to alternatives like edit_draft or publish_draft, nor state when not to use it. Some reasoning is left to the agent.

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