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

Annotations already declare readOnly/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: the blocking wait semantics via waitMs, the list-recent-jobs fallback when jobId is absent, and the concurrency constraint ('at most 2 video jobs run at once'). It omits any indication of the result shape, which keeps it from a 5.

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 clauses, front-loaded with the core purpose and free of filler. It is telegraphic and slightly clipped, but every clause carries information an agent needs.

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 must convey what comes back; 'progress and result' is a reasonable but thin characterization, and it does cover the alternate listing mode and concurrency limit. For a status-polling tool it is largely sufficient, though the result structure remains unspecified.

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 only 50%; jobId and waitMs carry no schema descriptions, while deviceId and workSessionId are documented in the schema. The description partially compensates by implying jobId selects the target job and that waitMs is the wait timeout, but it adds no format or default detail. This is a minimum-viable baseline, not full compensation 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?

The description names a specific verb+resource ('Progress and result of a video_edit or video_transcribe job') and explicitly distinguishes itself from siblings video_edit/video_transcribe, which it monitors. It also states the alternate mode ('Without a jobId, lists recent jobs'), so an agent can identify it precisely.

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 clearly signals the usage context — poll it after launching a video_edit or video_transcribe job, optionally blocking up to waitMs. However it names no explicit alternative (e.g. video_cancel for aborting) and gives no when-not guidance, so it stops short of a 5.

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