screenstudio_transcript_generate

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

Goes beyond the annotations by spelling out exactly what is destroyed (the current transcript, including caption fixes made elsewhere), what the generator can trigger (a model download, consistent with openWorldHint), and what the caller gets back (editor is 'updated' or 'not-open'), which substitutes for the missing output schema. This is unusually rich for a destructive write.

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 action and default, then the override condition, then the destructive consequence, then the return value. Dense and mostly waste-free, though the return-value sentence about 'editor' reads as a trailing detail that could be tighter.

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 destructive, open-world tool with no output schema, it covers the destructive scope, the network side effect, the fallback/override behavior, and the return value. Remaining gaps are minor: locale semantics and any precondition that a recording/audio source exists.

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 description coverage is 0%, so the description carries the burden; it does well for generator, giving the shape {type:'whisper', model} and the model-download implication, but says nothing about locale or what projectPath must point to. Partial compensation for a 3-parameter, nested-object schema.

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: transcribe the microphone using Screen Studio's own recognizer, and names the source of captions. It is clearly distinguishable from siblings screenstudio_transcript_read (reads) and screenstudio_transcript_edit (edits), and it explicitly situates itself in that family.

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 a clear default ('on-device system recognizer, no upload') and the condition for overriding it ('pass a generator ... only when the person wants it'). It also flags the sibling interaction by warning that it replaces caption fixes made with screenstudio_transcript_edit, though it does not state prerequisites (e.g. an existing recording) or when not to run it at all.

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