media.audio.voice

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

With no annotations provided, the description carries the full behavioral burden. It only reveals that the job is 'durable' and submitted asynchronously, but it does not disclose whether a job ID is returned, how results are retrieved, whether the operation is non-blocking, what failure modes exist, or any rate/cost limitations. This is insufficient for a tool with no other behavioral metadata.

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 entire description is one sentence and every word contributes: it identifies the action, the resource, and the job's durable/asynchronous nature. There is no fluff, repetition, or irrelevant detail.

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 tool with no annotations, an empty property schema, no output schema, and a single required parameter, the description is too sparse. An agent would not know what the required 'text' should look like, what the tool returns, or how to observe the result of the 'durable job' (e.g., via media.job.status).

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 input schema requires 'text' but provides no property description in 'properties' (which is empty). The description never explicitly names 'text' or explains its expected format, length limits, or language support. 'TTS' hints that text is the content to synthesize, but the core input remains undocumented at both schema and description levels.

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 a specific verb ('Submit') and resource ('durable voice/TTS generation job'), clearly identifying it as a text-to-speech/voiceover job submission tool. This distinguishes it from sibling tools like media.image.generate, media.video.generate, and media.audio.music, though it does not explicitly name an alternative.

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?

The intended use case—voice/TTS generation—is implied by the phrase 'voice/TTS', which differentiates it from music or visual generation tools. However, there is no explicit when-to-use guidance, no exclusions, and no indication of when to prefer this over job-control siblings like media.job.run_once or media.audio.music.

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