generate_speech_stream

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

No annotations are supplied, so the description carries the full burden. It usefully discloses that audio is persisted to a file and that streaming does not exempt the call from paid-operation gates, which is real behavioral context. It stops short of explaining what happens when allow_paid is false (error vs. silent refusal), whether files are overwritten, or any permission requirements.

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?

Two short, front-loaded sentences with no filler, and the paid-gate caveat is placed as a qualifying clause where it belongs. The brevity borders on under-specification, but nothing written is wasted.

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 9-parameter tool with a nested object, zero schema descriptions, no annotations, and no output schema, the description leaves nearly all calling decisions undocumented. An agent would have to infer the meaning and consequences of allow_paid, allow_unknown_cost, output_format, and voice_settings entirely from bare property names.

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 0% across 9 parameters, including a nested voice_settings object and the consequential allow_paid / allow_unknown_cost booleans. The description only obliquely gestures at two of them ('save its resulting audio' for filename, 'paid-operation gates' for the allow_* flags) and says nothing about text limits, output_format, model_id, language_code, or voice settings.

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 names a specific action and resource: call the streaming TTS endpoint and save the resulting audio. That is enough to distinguish it as the streaming speech-synthesis variant, but it never differentiates itself from close siblings like generate_speech or generate_speech_stream_with_timestamps.

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 explicit guidance on when to choose streaming over non-streaming, or this tool over generate_speech_stream_with_timestamps. The only usage-adjacent signal is the paid-operation caveat, which implies gating but doesn't tell the agent when or how to satisfy it.

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