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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so safety is partly covered; the description still adds real behavioral context the annotations lack: the 20 MB size ceiling, the public-URL requirement, and that output shape varies by response_format. Auth needs and whether the call is synchronous or returns a job id remain undisclosed.

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?

Three dense sentences, front-loaded with the core capability, then input constraints, then output-format behavior. No filler or restatement of the title.

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 explains what response_format values yield (timestamped segments, subtitle files), and it covers size and source limits plus the sibling escape hatch. The one gap is execution model — whether this returns the transcript directly or a job handle to poll via get_job.

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 80%, so the baseline is 3; the description exceeds it by explaining the response_format enum values that the schema lists without any description, and by restating the audio_url constraints (public https or data: URL, 20 MB cap). It adds nothing for model, prompt, or language, which the schema already documents.

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 ('Speech-to-text with any OceanToken transcription model') and immediately bounds the input source (public https or data: URL, up to 20 MB). It also names the sibling that handles the excluded case (upload_file for local files), so an agent can distinguish it without opening a schema.

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?

Explicitly routes local-file users to upload_file and conditions response_format choices ('verbose_json' for timestamped segments, 'srt'/'vtt' for subtitles). It gives clear context but stops short of stating when not to transcribe at all or how this interacts with the job-oriented siblings like get_job.

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