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

The description contradicts annotations: 'Submit' implies a write/mutation, but annotations include readOnlyHint=true, indicating a read-only operation. This is a flagrant contradiction. Additionally, no disclosure of idempotency behavior (despite idempotentHint=true) or auth/rate limits.

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?

Two sentences, front-loaded with purpose, no wasted words. Every sentence provides essential information.

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?

Given the tool's complexity (4 parameters, output schema exists), the description covers format support, language auto-detection, and diarization. However, the critical transparency gap (annotation contradiction) and lack of behavior details (e.g., idempotency handling) reduce completeness.

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 100% with individual parameter descriptions. The description adds value by summarizing supported formats (MP3, WAV, etc.), auto-detection of 99 languages, and optional speaker diarization (AssemblyAI), providing context beyond the schema.

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 clearly states the action (submit audio URL), the result (returns transcript_id for status/results), and distinguishes from sibling tools audio.transcribe.result and audio.transcribe.status by focusing on the submission step. It also lists supported formats and optional diarization.

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 indicates that after submission, one should use the returned transcript_id to check status and retrieve results, implicitly guiding usage toward sibling tools. However, it lacks explicit when-not-to-use or exclusion criteria.

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