screenstudio_narrate

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

Goes well beyond the annotations: it discloses that line text leaves the Mac via an online Microsoft voice service (matching openWorldHint), that the app's own AI/recorded voiceover tracks are disabled, how mixing/music ducking and caption file outputs work, and what the return value reports (start/end, choices, warnings). It also defines the re-sync state-retention rules.

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 organized into behavior, pinning, captions, return value, and re-sync. It is dense and long, with several multi-clause sentences, but virtually every clause carries decision-relevant information rather than padding.

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?

For a 10-parameter mutation that performs network speech synthesis and retimes audio, the description covers side effects, privacy, dependencies on marker-producing tools, caption output modes, return contents, and re-sync semantics. With no output schema, it still explains what comes back.

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 high (80%), so baseline is 3, but the description adds semantics the schema omits — notably the sourceMs vs playbackMs distinction ('stays on its moment through later edits') and the pinToMarkers 300ms/marker-i rule including the skipped-marker edge case. It does not explain line limits or the nested text constraints, so not a full 5.

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?

Opens with a specific verb+resource ('Voice over the video') and then distinguishes itself from siblings by noting Screen Studio's own AI and recorded voiceover tracks are disabled and that music laid by screenstudio_music stays under the voice. An agent can tell this apart from screenstudio_music and the voice/caption siblings 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?

Gives clear operational context: call again without lines after changing the cut to re-sync, re-sync keeps last voice/rate/music/volumes/captions unless overridden, and markers come from screenstudio_desktop_perform markers:true or screenstudio_record_control addMarker. It does not explicitly state when to prefer this over related narration siblings, so it stops short of full alternative routing.

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