transcribe

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

With no annotations, the description carries the full burden; it does disclose two real behaviors: an optional dependency install is required, and results are cached rather than returned for direct consumption. It omits whether this is long-running or expensive, whether it mutates project state, and how the model choice affects speed/accuracy.

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?

Two short sentences, front-loaded with the action and its output, then the prerequisite and the read-back path. Nothing is wasted or buried.

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 mutation-style tool with no output schema and zero-documented parameters, the definition covers the call/read workflow and the install requirement, which is the most important framing. It still leaves open the parameter tradeoffs (model, language) and whether the call blocks or returns a status, so an agent can call it but not call it well.

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 and largely does not. It implies asset_id via 'an asset' but says nothing about the model (default 'base'), language (nullable, presumably auto-detect), or project parameter, leaving three of four parameters without meaning beyond their names.

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 gives a specific verb and resource ('Transcribe an asset') and adds the distinguishing output trait 'word timestamps', which separates it from get_transcript (reading) and import_transcript (bringing in existing transcripts). It stops short of explicitly naming those siblings as alternatives, but the object is unambiguous.

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?

It states the prerequisite ('needs pip install reelwright[transcribe]') and the follow-up pattern ('Results are cached; read them with get_transcript'), so an agent knows both what to install and what to call next. No explicit when-not guidance or cost/runtime expectation is given.

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