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

With no annotations, the description carries the full burden and does so: accepted input forms (https URL or base64 POST), supported formats, 10 MB cap, ~100 languages, billing model ($0.02/call over x402 USDC, charged only on delivery), and no API key/account required. These are exactly the prerequisites and cost constraints an agent needs before invoking a paid external service.

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?

Front-loaded with the usage trigger, then input specs, then return values and pricing – a sensible order and no filler sentences. It is a single very dense sentence chain with semicolons, which costs a bit of scannability.

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 takes responsibility for describing returns (text, detected language with probability, duration, timed segments, optional word timestamps), plus cost and auth. Nothing an agent needs to call this correctly is missing.

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%, so the schema already documents url, audio, words, and language. The description restates the format list and the words=true behavior but adds no syntax or edge-case detail 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?

States a specific verb+resource ('speech-to-text', 'handed audio and needs text') and names the concrete engine (Whisper large v3 turbo). It is clearly distinguishable from siblings like ai_speech and ai_translate, which handle the opposite or a different transformation.

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?

'Use when an agent is handed audio and needs text it can work with' gives a concrete triggering condition. It does not name an alternative or an explicit when-not case (e.g., when to reach for ai_translate instead), so it stops short of full routing guidance.

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