generate_speech

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

With no annotations, the description carries the full burden. It usefully warns that the call consumes credits and can be blocked by dry_run or missing paid authorization, but it does not explain the interplay between allow_paid and allow_unknown_cost, whether credits are charged on failure, or what happens to an existing file with the same name. Given nine parameters and a nested voice_settings object, the behavioral picture is thin.

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 sentences with the core action front-loaded, so it is compact. However, the second sentence is grammatically garbled ('blocked by dry_run or either missing paid authorization gate'), which forces the reader to parse ambiguous logic in the one sentence carrying the behavioral content.

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 nine-parameter mutation tool with a nested settings object, no annotations, and no output schema, the description covers only the credit/gating behavior. It omits where the file is written, whether the same filename overwrites, default output format implications, and any return value information, so an agent cannot confidently construct a valid call from it.

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 nine parameters, so the description must compensate. It gestures at the paid-gating concept implied by allow_paid and allow_unknown_cost but never explains voice_id, filename (destination path?), output_format, model_id, language_code, or voice_settings, leaving several parameters with no documented meaning anywhere.

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 definition gives a concrete verb and resource: 'Generate and save speech audio,' which implicitly distinguishes it from the streaming and timestamped siblings by emphasizing that output is saved. It does not explicitly name those siblings (generate_speech_stream, generate_speech_with_timestamps), so the differentiation is inferential rather than stated.

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 discloses prerequisites (dry_run must be disabled and paid authorization gates must be satisfied) which tells the agent when the call will fail, but it never says when to pick this over generate_speech_stream, generate_dialogue, or the timestamped variants. Usage context is implied by the saving behavior rather than spelled out.

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