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

Beyond the annotation values, the description discloses a real side effect: 'This bills the authenticated user.' It also explains the inline-audio output and client compatibility caveat, and points to get-generation for cost afterward. That gives the agent materially useful behavioral context that annotations alone do not provide.

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 description is compact and front-loaded: the core function and output type appear first, followed by billing and the discovery workflow. Each sentence contributes essential operational or discovery information; there is no filler or redundancy.

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 generative audio tool with no output schema, this description covers invocation prerequisites, how to get the right inputs, what to expect in the response, cost implications, and potential client limitations. An agent has enough information to reason about using this tool and checking results.

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 already 100%, so the baseline is solid. The description adds value by explaining how to find valid model and voice values: find models with output_modalities=speech and fetch supported_voices via get-model. This directly helps an agent select values for required parameters rather than only knowing their types.

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 uses a specific verb (synthesize) plus a clear resource (speech from text), and explains the audio content-block output. This cleanly distinguishes it from sibling tools like generate-image and transcribe-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?

It tells an agent the exact discovery workflow: list TTS models via list-models with output_modalities=speech and find voices via get-model. It also calls out a client-side constraint ('not all MCP clients can play audio') that helps decide whether this tool is appropriate. It does not explicitly exclude alternatives such as transcribe-audio, but for generation the intended path is clear.

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