add_voice

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

With only readOnlyHint=false supplied, the description carries most of the burden and delivers: it discloses the written artifact, that the mixer consumes the timing/mouth-envelope data, and critically that it 'Replaces any earlier narration' — a destructive side effect an agent must know before calling. It omits failure behavior when no provider/file is available.

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 tight sentences, all front-loaded: purpose first, then the file-vs-text rule, then the output, then the replacement warning. Some domain shorthand ('vo/timing.js', 'mouth envelope') is opaque but necessary for correctness rather than 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 mutation tool with no output schema and only a single annotation, this covers the essentials: what gets written, what gets thrown away, and what inputs are required versus optional. The remaining gaps (behavior on invalid `project`, error mode when neither file nor provider is available) are real but secondary.

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 33%, so the description must compensate, and it partly does: it explains that `file` may be a recording or output from any TTS tool, and that `text`-only lines fall back to the server's env provider. It says nothing about `project` (the other undocumented required parameter) or how `gap` interacts with lines that have `at`.

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?

States a specific verb+resource ('Add narration') and immediately scopes it away from visual media by defining what a line is (a `file` or `text`). It also names the artifact produced ('vo/timing.js') and the downstream step ('the mixer places the clips'), which separates it from siblings like add_media. It stops short of explicitly naming the sibling to use for non-narration audio.

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?

Offers real precondition context: no voice ships with the server, and 'Current provider: none', which tells the agent that text-only lines cannot work here and files must be supplied. However, it never states when to choose this over a sibling or what to do when no provider is configured — the agent must infer that external TTS audio is the only viable path.

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