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

Annotations only convey read/write/destructive hints, while the description adds meaningful behavioral context: longer audio is rejected before an upstream call, each call costs 5 MESH, and the tool is powered by xAI while being unaffiliated. This goes beyond the structured annotations, though it does not describe the exact output format or error behavior.

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 core function and key constraint are front-loaded in one clear sentence. The trailing legal/branding line ('Powered by xAI. Not affiliated...') and pricing tag add useful context but are not strictly necessary for tool invocation, making the description slightly less concise than it could be.

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?

Despite having only one parameter, the tool is not fully invocable from the description alone because the input payload structure for the WAV audio is undefined. There is no output schema, and the schema's input description is a generic placeholder, so critical usage details are 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?

The schema only defines a generic `input` object with examples for unrelated tools like agent-brain and agent-memory, which is misleading. The description adds that the input is WAV audio and limited to 5 minutes, but it does not specify how the audio should be represented in the payload—whether as a URL, base64, file path, or nested object—leaving a critical invocation gap.

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 opens with a specific verb and resource: 'Transcribe up to 5 minutes of WAV audio to text.' This clearly distinguishes the tool from siblings like grok-tts and voice-tts-stt-placeholder by stating exactly what audio input it accepts and what it produces.

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?

The description gives a clear boundary condition ('Longer audio is rejected before any upstream call') and cost context, so an agent knows not to submit long audio. However, it does not explicitly mention when to prefer this over alternatives such as grok-tts or other voice tools, leaving the comparison to inference.

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