Speak one line in the character's voice (paid)

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

With no annotations, the description carries the burden well: it discloses that the call is paid with a concrete rate (≈$0.10 per 1000 characters), that only one line is produced per call, and that a file is written to assets/voice/lines/<name>.mp3, so the agent knows an artifact is created and a cost is incurred. It does not say what is returned (path? duration?) or what happens on overwrite, which keeps it below a 5.

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?

Extremely dense for its length: gating condition first, then cost, then output location, in one front-loaded fragment. Slightly telegraphic ('after character_voice' without a noun) and could read more cleanly, but every clause earns its place.

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 paid, artifact-producing tool with no annotations and no output schema, the description covers cost, prerequisite, unit of work, and destination path — the essentials. It leaves open what the call returns and whether a partial/failed call is still billed, which matters for a cost-bearing action.

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 67%, so the schema already documents text and name reasonably; the description still adds meaning by tying <name> to the saved file path, which is not obvious from the schema. The 'id' parameter remains unexplained in both places, so the gap is only partly closed — baseline 3 fits.

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 core action is only implied: 'one line per call' plus 'Saves assets/voice/lines/<name>.mp3' lets an agent infer audio generation, but the description never states a verb like 'generate' or 'synthesize'. The prerequisite reference to character_voice does help separate it from the character_video/character_translate siblings, but the purpose rests largely on the title.

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?

'ONLY on request, after character_voice' gives both a hard gating condition and the sequencing prerequisite, which is unusually explicit for this catalog. It stops short of naming when to pick character_voice_translation instead, so it is not a full alternative routing rule.

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