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

Goes well beyond the readOnly/openWorld/idempotent annotations: discloses voice-activity filtering, that audio is not stored, the exact price and chain, the x402 payment handshake, and that a 503 on capacity exhaustion is not charged. These are the non-obvious behaviors an agent needs before spending money.

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 operation and its hard limits, then payment and capacity details. It is dense and mostly earns its length, though the trailing 'Same tool over HTTP' note is peripheral to an MCP caller.

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 still specifies the return fields (text, language, duration, optional segments + WebVTT) and covers cost, failure modes, and the payment retry loop, which is everything needed to invoke it correctly.

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 coverage is 75% and already documents language, audio_url, and audio_base64. The description mainly restates the two audio inputs and hints that 'segments' toggles segment + WebVTT output, but does not explain the segments enum (string 'true'/'false') or any mutual exclusivity between audio_url and audio_base64.

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?

Names a specific verb and resource ('Transcribe one audio file'), the exact model (Whisper large-v3-turbo), the accepted formats, and the one-megabyte limit, so it is clearly separable from ai_image, ai_classify, and other siblings in the ai_* family.

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?

Constraints on when it is applicable are explicit: file formats, 1 MB cap, public https URL or base64 input, and the retry path via params._meta["x402/payment"] when an unpaid call returns PaymentRequired. It stops short of naming a sibling alternative (e.g., HTTP endpoint or another transcription option), so it is context-rich but not fully comparative.

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