text_to_voice_preview_stream

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description usefully discloses the concrete return payload (audio/mpeg bytes) and that output_path persists them, but says nothing about streaming behavior, size limits, or auth.

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?

A single front-loaded sentence with no padding; the return type is stated before the optional parameter hint. It loses a point only because the leading phrase is a near-verbatim restatement of the title rather than new information.

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?

There is no output schema, so the description correctly covers the return type (audio/mpeg bytes) and the save-vs-inline tradeoff. However, for a streaming preview tool it never explains what the preview represents or when an agent should call it rather than the non-streaming voice-preview siblings, leaving the definition merely adequate.

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 description coverage is 100% and the schema already explains output_path resolution (ELEVENLABS_OUTPUT_DIR, inline base64 fallback) and generated_voice_id. The description only echoes the output_path behavior, adding no meaning beyond the schema, so the baseline 3 applies.

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 restates the tool name ('Text To Voice Preview Streaming') and adds only that it returns audio/mpeg bytes. A reader can infer it streams preview audio, but the description never says what is being previewed or how this differs from the many sibling text_to_voice*/text_to_speech* tools.

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?

There is no when-to-use guidance at all — no condition, no alternative, no prerequisite such as needing a previously created generated_voice_id. With ~15 similar audio-synthesis siblings, the absence of routing guidance is a real gap.

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