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 auto-invocation by import_actor, that the model has built-in language identification, and the real-world failure mode (clone models dropping sentence tails) that motivates verification. It stops short of stating cost/latency or error behavior, so not a full 5.

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-loads the core behavior, then uses clearly sectioned blocks for uses and parameters. The script-verification rationale is slightly verbose but each sentence contributes useful context, so only marginally over-length.

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 not be explained. Purpose, both parameters with constraints, and both usage modes are covered, leaving nothing an agent needs in order to call this correctly.

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 does: audio_path is a local path restricted to WAV, and language is an optional hint (zh/en) whose default is model self-detection, with guidance to supply it only when a dialect is misclassified. 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?

States a specific verb+resource+output: listen to a recording and return the spoken text as words. It also distinguishes itself from siblings by clarifying it is for verification, not subtitle production, and that import_actor invokes it automatically.

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?

Enumerates two concrete when-to-use scenarios (checking reference audio during import, validating a dubbed line against its script text) and explicitly excludes the wrong use case ('核对' not '生产字幕'). It also names how it relates to import_actor's automatic invocation.

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