transcribe_to_captions

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the read source (word timings in <source>/.media), the write side effects (SRT written to "<project folder>/Phụ đề/<sequence>.srt" and a caption track added), and an exclusion rule (slate calls outside takes are dropped). It does not say what happens if timings are missing or whether an existing caption track/SRT gets overwritten.

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?

Purpose and data source are front-loaded, and every clause carries information (output path, language agnosticism, slate exclusion, post-edit step). The middle sentence is dense and parenthetical-heavy, which slows scanning, but nothing is truly wasted.

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 tool with five optional parameters, no annotations, and no output schema, the description covers inputs, side effects, output artifact path and post-processing expectations. The main remaining gap is the return value/diagnostic behavior when no word timings exist.

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 100%, so baseline is 3, but the description adds real meaning: maxChars governs line splitting, sourceTrack defines which clips contribute, and addTrack is implicitly linked to 'added as a caption track', plus sequence name maps to the output filename. Sequence ID/name resolution is only partly covered.

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 (make captions for a cut) and explains exactly where the content comes from: word timings written by rough_cut_by_cues or describe_sources. It also names the downstream artifact (an SRT in the project folder plus a caption track), which no sibling tool does.

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?

The prerequisite chain is clear: word timings must already exist in <source>/.media, produced by rough_cut_by_cues or describe_sources, and the text is polished afterwards in Premiere's Text panel. It never explicitly names when to prefer this over the sibling create_caption_track, so the alternative selection is left implicit.

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