klax_get_video_transcript

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

With no annotations provided, the description carries full burden. It discloses the fallback behavior (local video path if not indexed), the STT attempt with faster-whisper/whisper, the unsupported status when STT library is missing, and explicitly states it does not download remote URLs or call external cloud APIs. This is substantial behavioral disclosure beyond what annotations would provide.

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?

The description is a single paragraph but front-loaded with the core purpose, then systematically explains fallback, time filtering, and constraints. Every sentence adds value; there is no filler. Slightly long but appropriately detailed for a tool with nuanced behavior.

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?

Given the tool's complexity (indexed vs local, STT fallback, time-range filtering) and the presence of an output schema, the description covers the key scenarios and error conditions (unsupported STT). It does not exhaustively cover edge cases like invalid local paths, but the main use cases are well documented.

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 0%, so the description must compensate. It explains the dual meaning of material_id_or_video_id (indexed ID or local path), and specifies the accepted time formats (HH:MM:SS or MM:SS) for start_time/end_time. It also clarifies how time ranges filter chunks. This adds meaning well beyond the bare 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?

The description clearly states the tool retrieves subtitles/STT transcripts for indexed lecture materials or local video paths, with optional time-range filtering. It uses a specific verb (조회/query) and resource (transcript), and while it doesn't explicitly name sibling tools, the scope is unambiguous and distinct from any other sibling.

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 description explains when to use the tool (when transcript of indexed material or local video is needed) and how it chooses between the two sources based on existence in the index. It does not mention alternatives or exclusions, but the context is clear enough for an agent to decide.

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