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

Annotations only declare readOnlyHint and openWorldHint, so the description carries extra weight and does so: it discloses the 20 MB input cap, the output payload (transcript, detected language, timed segments, WebVTT subtitles), and the per-call cost ($0.047 USDC via x402). It does not mention rate limits, timeout behavior for long files, or what happens on failure, so not a 5.

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 capability, then inputs, then outputs, then pricing. Dense but every clause carries information; the pricing sentence is the busiest part but still earns its place for cost-sensitive callers.

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?

With no output schema, the description usefully enumerates the return fields and the cost model, matching its complexity well. The only gap is the unexplained 'max_minutes' reference that has no counterpart in the input schema, leaving the agent unsure whether that parameter exists.

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 baseline is 3; the description reinforces the url/base64 alternative and the 20 MB limit but adds no format or syntax detail beyond the schema. It also references a 'max_minutes' parameter (default 6, up to 30) that does not appear in the input schema, introducing mild confusion rather than clarity.

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 capability ('Speech to text') plus the underlying model (Whisper large v3 turbo) and both accepted input modes, so the agent knows exactly what the tool does. It does not, however, name or differentiate itself from nearby siblings like transcribe_pro or audio_transcriptions, which is the only thing keeping it from a 5.

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?

Gives clear invocation conditions: provide a public audio/video URL or base64 audio, with a 20 MB cap and supported formats listed. It also surfaces pricing constraints (default 6, up to 30 minutes) that shape the decision, but never states when to prefer this over transcribe_pro or audio_transcriptions, so no explicit alternatives.

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