transcribe

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

With no annotations, the description carries the burden well: it discloses that timestamps are on the CURRENT timeline and shift after cuts, and that the first run per file is slow and may download the model while later calls are instant. It stops short of saying whether results are cached to disk, whether the operation mutates project state, or what the transcript looks like.

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 action and timestamp behavior, then usage, then parameter hints, then performance notes. Dense but every sentence carries information; minor tightening possible.

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 6-parameter tool with no annotations and no output schema, the description is decent but incomplete: it never describes the return shape (plain text vs. segments vs. word list) or what refresh actually does, both of which an agent needs before calling.

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 include_words, vocabulary, and vaguely start/end ('limit the window'), but never states units or defaults for start/end. Two parameters — refresh and language — are entirely unexplained, which is a real gap at zero coverage.

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 what's said in the storyline') plus the engine and timestamp behavior, so an agent can tell it apart from editing tools like cut_ranges or find_silences. It does not explicitly differentiate itself from the sibling find_repeats, even though it claims to help 'find repeated takes,' leaving a small ambiguity.

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 concrete usage context ('Use it to find repeated takes, flubs and filler') and a conditional recommendation for include_words with start/end to limit the window. No explicit when-not guidance or named alternative is provided.

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