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

With destructiveHint=true and idempotentHint=false already declared, the description adds real substance: 'each run is a new version', and for analyze the nuance that existing assets (description, reference image, voice) are preserved, new ones added, and orphaned assets persist until the user deletes them. That non-obvious side-effect behavior is exactly the kind of context annotations cannot carry.

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?

Front-loads the two mode labels and keeps each block to two or three sentences with no filler. Minor jargon ('voice blocks') and backticked direction syntax add density but the structure is easy to scan.

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?

Covers the semantics and side effects of both modes and routes the agent to script_read/assets_read for inspection, which compensates for the absent output schema. The generation-tuning params (model, settings, editable_sections) are left entirely to the schema, but they are fully annotated there.

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%, so the schema already documents model, settings, project_id and editable_sections; the description adds nothing about them. It only restates the action enum, which the schema also describes, so 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?

Both modes are stated with specific verbs and resources: 'generate' writes the script from the brief/narrative style and 'analyze' extracts characters, environments and objects and splits into voice blocks. The resource ('the script') separates it from storyboard_generate/style_generate/voiceover_generate, but the description never explicitly contrasts itself with those sibling generators, so differentiation is left to the reader.

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 clearly frames the two selectable actions and points at the follow-up tools ('review it with script_read', 'Review with assets_read'), which gives an agent a usable workflow. It stops short of stating when to prefer generate vs analyze or any exclusions/prerequisites, so no full 5.

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