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 richly: single-call design (no upload step, no polling), error semantics (no speech yields a 400 and no charge), size/duration limits, and the payment model (USDC on Base, no account, no API key, $0.30 per file). These are exactly the behavioral facts an agent needs before invoking.

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 core purpose and output, then folds pricing, formats, limits, and payment into the remaining text. Dense but every clause carries information; slightly verbose with the trailing payment sentence but no filler.

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 no-output-schema transcription tool, the description covers inputs accepted, output contents (transcript, timed segments, detected language, optional WebVTT), limits, failure behavior, and payment prerequisites. Nothing essential to correct invocation 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/file_base64 and the optional fields. The description reinforces 'send a url or base64' and the accepted audio formats but adds no parameter-level detail (e.g., language-code format) beyond the schema, so the baseline 3 is appropriate.

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 and resource: 'Speech to text' converting named audio formats into a transcript with timed segments and detected language. The scope (max 5 MB, ~5 minutes) and output shape make it immediately distinguishable from the other document/media tools like doc_ocr and doc_to_markdown.

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?

Clearly frames the use case (transcribing audio via url or base64 in one call, no upload or polling), which tells an agent exactly when this applies. It does not explicitly name a when-not or an alternative sibling, but no sibling offers transcription, so the practical gap is small.

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