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

Annotations already declare non-readOnly, non-idempotent, non-destructive, and the description is consistent with them while adding real behavioral detail: each run creates a new version, and analyze preserves existing assets (description, reference image, voice) and adds new ones while stale assets persist until the user deletes them. That side-effect disclosure goes meaningfully beyond the structured fields, though permissions and failure behavior are unstated.

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 two modes are front-loaded and labeled, and the follow-up read tools are attached to the relevant mode. The parenthetical about [SCENE: ...] directions is useful but slightly dense; overall it is tight and earns its length.

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 two-action mutation tool with full schema coverage and no output schema, the description covers what each action does, how versions behave, what analyze does to existing assets, and which read tool verifies each result. Nothing essential for correct invocation is missing.

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 enriches the meaning of the `action` enum values considerably, but says nothing about the other four parameters, so it only marginally exceeds the baseline.

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 names the two modes explicitly (generate: write the script; analyze: find characters/environments/objects and split into voice blocks), giving a specific verb+resource for each. It also names the sibling tools used to inspect results (script_read, assets_read), so an agent can place it in the workflow without opening the 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 tells the agent what each action is for and how to follow up (review with script_read, review assets with assets_read), plus the important context that each generate run produces a new version. It does not address when to prefer script_edit over re-generating, nor any prerequisites, so the routing guidance is clear but not exhaustive.

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