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

Beyond the annotations it explains exactly what happens: the voice is cut from the recording rather than synthesized, an on-scene presenter face is replaced, and re-selecting the same take is a no-op (matching idempotentHint). It also discloses typed refusal reasons, feature gating (`forbidden`, `no_ofrecido`) and that refusals change nothing — behavior an agent cannot get from `destructiveHint: true` alone.

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 core effect is front-loaded in the first sentence and every following clause adds information (idempotency, refusal codes, permissions, cost). It is dense and includes one very long sentence with untranslated error tokens, which slightly taxes readability but carries no filler.

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 destructive, owner-only mutation with no output schema, the definition covers effect, permissions, idempotency and error taxonomy. The one gap is that it does not explicitly state whether the scene's previously chosen voice is discarded — implied by "gives way to it" but not spelled out for a `destructiveHint: true` operation.

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?

The schema already documents asset_id (one of the scene's takes) and scene_index (0-based), and the description largely restates the 0-based fact. It does add the relational meaning that the asset must be a take belonging to that scene within that project, but `project_id` remains undocumented anywhere. Baseline 3 for 67% coverage with modest added meaning.

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 a specific verb and resource: it makes an already-recorded take "the scene's voice" and states the concrete effect (spoken segment used, picture shown when available). It is clearly distinct from list_takes or assign_narration in substance, though it never names those siblings directly, so the agent must infer the boundary.

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 gives real usage context: the effect lands "in the next production," only the piece's owner may call it, and it requires `write`. It also states the re-choose case changes nothing. What's missing is an explicit comparison to the other routing tools (assign_narration, assign_material) that an agent might otherwise reach for.

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