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

Goes well beyond the annotations by disclosing the privacy-relevant behavior (on-device vs. Apple's remote speech service, 'audio may leave the computer'), the asynchronous job model (background job, jobId, waitMs timeout), and the write/no-write boundary. Annotations only carry safety flags; the description carries the operational reality.

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 purpose and outputs, then progressively adds async, privacy, and write-boundary details. It is dense and slightly run-on in the final sentence, but nearly every clause carries decision-relevant 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?

With no output schema and a 7-parameter async tool, the description covers return values (text, cues, SRT), the long-job path (jobId + video_status), and side-effect boundaries. Nothing critical for correct invocation is 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?

Schema coverage is 57%, and the description adds real meaning for waitMs (a timeout, with fallback to video_status/jobId). But other under-documented parameters (path, maxSeconds) gain no extra explanation, so it only partially compensates for the coverage 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?

States a specific verb and resource ('Transcribe the speech in a video or audio file into subtitles') and names the concrete outputs (text, caption cues, SRT). It clearly distinguishes itself from adjacent video_* siblings by naming video_edit (consumes captions) and video_status (delivers long-job results).

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?

Gives clear context: use it to produce timed captions, and if the file is longer than waitMs, poll video_status instead of re-calling. It stops short of explicit when-not-to-use guidance or comparison to any non-video alternative, so it lands just under the top bar.

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