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

The description clearly states the operation is asynchronous (returns envelope immediately, requires polling) and describes the output (SRT). While there are no annotations, the async behavior is core and explicitly disclosed. It also mentions handing the SRT URL to a transcode filter, revealing integration behavior. No annotation contradiction. Missing job envelope details like job ID field not named, but for transcription it's strong.

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 sentences: outcome, async pattern with explicit polling instruction, downstream integration. Dense and front-loaded.

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?

Describes the async flow and result type, and names the follow-up tools. It doesn't mention the job envelope shape, completion conditions beyond status='completed', authentication, or SRT URL expiry. But given schema and sibling names, it's adequate for use.

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 covers all parameters at 100%, so baseline 3 is appropriate. The description adds context that the input is audio or video and output is SRT, but doesn't add detail about the task/language parameters beyond what the schema already provides.

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 states a specific action and resource: generate an SRT subtitle file from an audio or video URL using Whisper. This clearly distinguishes it from siblings like transcode_video and run_blueprint_run, and the downstream references to get_transcribe/get_transcribe_download clarify its role.

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?

It explicitly maps the async workflow: call to get a pending envelope, poll get_transcribe until completed, then use get_transcribe_download. It also explains why you'd use this and how the output integrates with transcode's subtitles parameter.

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