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

Annotations only cover the safety profile (write, open-world, non-idempotent, non-destructive); the description adds substantial behavior beyond them: required dependency ordering, the skip of already-generating blocks, the constraint that the model must match the project's voice engine, and the side effect that an existing storyboard retimes automatically.

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?

Four short sentences, the core action front-loaded, and each clause carries a distinct constraint (prerequisites, default scope, model rule, retiming). Slightly terse/fragmented phrasing ('and every asset a reference image') costs a little readability but not content.

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 six-parameter mutation tool with no output schema, the description covers prerequisites, default behavior, the model constraint, and the storyboard side effect. It leaves out failure modes (e.g. missing voice/reference image handling) and what a successful run returns, but annotations and the dry_run parameter cover most of the remaining ground.

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 coverage is 100%, so baseline is 3, but the description adds value the schema lacks: the re-generation semantics of voice_block_ids ('again if they have audio' vs 'omit for every block without audio') and the hard constraint that the chosen model must match the project's voice engine.

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 opening 'Generate voice block audio' gives a specific verb plus resource, and the surrounding constraints (blocks, speakers, reference images, retiming) make clear this is the audio synthesis step rather than a settings edit. It does not name the sibling it should not be confused with (voiceover_edit / voiceover_read), so it stops short of full differentiation.

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 states real prerequisites ('Every speaker needs a voice first, and every asset a reference image') and the selection condition for voice_block_ids ('without ... it fills every block with no audio'). No explicit when-not or named alternative is given, so the agent must still infer that voiceover_edit handles post-generation changes.

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