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

Beyond the readOnly and non-destructive annotations, the description reveals that it requests microphone access, streams audio to the platform, does not store the audio, and has a fallback to a URL button. This adds crucial behavioral expectations not captured by annotations.

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 somewhat verbose, with multiple clauses and parentheticals, but it is logically organized and each sentence adds necessary context. It front-loads the core purpose and then explains usage and fallback, maintaining clarity despite extra detail.

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?

The description fully covers the tool's role in the workflow, its interactive nature, data handling (not stored), fallback mechanism, and safety guarantee. It leaves little ambiguity about when and how to call it, and it does not need to explain a non-existent output schema.

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?

The schema already fully describes both parameters (engine and model_id) with detailed explanations and enum values. The description does not add parameter-specific insight, but the baseline of 3 is appropriate given full schema coverage.

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 clearly states the tool renders an in-chat live microphone tester for one library model, and explicitly frames it as a free test step between search and purchase. This distinguishes it from sibling tools like search_wake_word_library and buy_library_model, providing unambiguous purpose.

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 provides explicit usage context: 'Use after search_wake_word_library, before buying.' It also explains that only the human can run it (interactive), and describes fallback behavior when microphone access is unavailable, making it clear when and how to use it.

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