Get Video Transcript

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

Annotations already cover readOnly, idempotent, and non-destructive semantics, so the bar is lower. The description adds genuinely useful behavior beyond them: no translation or visual analysis is performed, offset/limit are character counts (not tokens or lines), and the language fallback order is original audio then authored captions.

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?

Terse and front-loaded: purpose first, then language selection, then pagination mechanics, then scope limits. Every line carries information, though the opening 'Continue reading' framing is a touch indirect for an agent that may be calling this cold.

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?

An output schema exists so return values need no explanation, and the description covers the non-obvious parts an agent needs: pagination via next_offset, character-based offsets, and language resolution. Only minor gaps remain, such as any rate-limit or caption-availability failure behavior.

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 25%, so limit and offset are undocumented in the schema. The description compensates by stating that offset and limit count characters and by naming next_offset as the cursor to loop on, plus explaining the language preference order when language is omitted.

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 (read/continue reading) and resource (timestamped source text for a video), and the tool name confirms it is the transcript reader. It distinguishes itself from get_video_context by positioning itself as the continuation mechanism, though the phrase 'timestamped source text' is slightly indirect compared to simply saying 'transcript'.

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?

Explicitly routes to siblings and conditions: use the language from get_video_context when continuing its transcript, use list_transcript_languages for exact codes, and repeat with next_offset until null. Both the 'when to use' and the pagination loop condition are spelled out.

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