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

Annotations already declare readOnlyHint=true, which matches a pure conversion operation. The description adds genuinely useful behavior the annotations don't carry: a cost of 50 points per call and that the result comes back as JSON. It stops short of describing latency, queueing, or failure modes.

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 kept short; the format list, return type, and cost are all useful. The English line and the Korean line largely duplicate each other, so some text is redundant rather than additive.

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 correctly notes that the result is JSON text. Parameters are fully covered by the schema, and cost is disclosed. Only the absence of usage context and any note on URL accessibility keeps it from being fully complete.

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%, so all three parameters (language, audio_url, artifact_filter) are already documented in the schema, setting the baseline at 3. The description adds little beyond restating formats, and its 'MP3, WAV, WMV' list is narrower and partly inconsistent with the schema's allowed MIME types (WMV is not permitted), so it doesn't meaningfully improve parameter understanding.

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+resource ('Convert a speech audio file to text (STT)') and names the supported input kind. This cleanly separates it from the sibling tts_* family (the opposite direction) and from text-extraction tools like ocr.

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?

Usage is only implied: it says what it converts but never states when to pick it over ocr, youtube_subtitle, or voice_change, nor any prerequisite such as needing a publicly downloadable URL. No alternatives or exclusions are named.

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