text_to_speech

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

With no annotations, the description carries the full burden, but it does disclose the async task model ('Returns a task id, status, and output URLs'), which helps the agent understand that results may not be immediate. It omits authentication requirements, cost implications (check_pricing is a sibling), rate limits, and what happens when wait=true blocks.

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, front-loaded with the action and followed by the return shape. No redundant restatement of the name or filler of any kind.

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 10-parameter tool with nested speaker and dialogue-turn objects, no annotations, and no output schema, the description is far too thin. It never explains the multi-speaker dialogue model, what wait defaulting to true implies for latency, or how callback_url and poll_interval_ms interact, leaving meaningful risk of misuse.

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 80%, so the schema already documents most fields, including the required speakers and dialogue_turns arrays. The description adds nothing beyond that, so the baseline of 3 applies; the two required parameters and their relationship (turn speaker_ids referencing configured speakers) are only explained in the schema.

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 and resource: 'Create a Gemini TTS task on RunAPI (text to speech).' That clearly distinguishes it from siblings like get_task, login, and check_pricing. It falls short of 5 only because it doesn't name a sibling as the alternative path for retrieving results.

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?

No when-to-use or when-not-to-use guidance is given. The description never mentions that get_task exists for retrieving results later, nor how wait=true versus callback_url changes the calling pattern. Usage must be inferred entirely from the tool name.

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