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

With readOnly, idempotent, non-destructive and closed-world hints already declared, the description adds genuinely new context: it spells out the two return shapes in the absence of an output schema, notes that `[SCENE: ...]` directions are 'never spoken', and exposes all_complete/reference-timing fields. It stops short of covering pagination or error behavior.

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?

Two tightly keyed clauses, 'voices:' and 'blocks:', are front-loaded with the action names so an agent can scan the right one immediately. The brace/field notation is compact and slightly telegraphic but wastes no sentences.

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 read tool with no output schema, the description usefully enumerates both result shapes and flags the non-spoken scene directions. The main gap is that it never states the project_id requirement for the blocks action or anything about size/limits, but otherwise it covers what an agent needs.

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 the input schema already documents every parameter, including the group filter ('large ElevenLabs catalog') and the bulky word-level timings flag. The description adds only marginal meaning (voice_id = the speaker's voice) and does not clarify that project_id is needed for the blocks action.

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 precisely what each of the two read actions yields: voices returns {groups, voices} for an engine, and blocks returns {blocks, total_duration_ms, all_complete}. That is a specific resource description tied to the action enum, though it never names a sibling (e.g. voiceover_edit / voiceover_generate) to differentiate the read path.

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?

There is no explicit when-to-use or when-not guidance and no mention of alternative tools. Usage is only implied by the action enum and its schema descriptions, so an agent can infer that 'voices' is for catalog lookup and 'blocks' for project data, but the description itself does no routing.

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