transcribe_batch

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals the interactive nature, previews, confirmation, file-saving behavior, format support, and privacy mode effects. However, it does not explicitly state whether confirmation is always required or only in certain modes, leaving a slight ambiguity.

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 well-structured: core function first, then details on behavior, supported formats, alternative tool, and privacy note. It is front-loaded and each sentence adds value, though it could be slightly more concise without losing information.

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?

The description lacks an explicit statement of what the tool returns (e.g., status, transcript, or metadata). It details the process but does not clarify the return value expected by the agent. Additionally, the flow of invoking multiple times to process all files is implied but not fully explained. Despite these gaps, it covers many practical aspects.

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?

All 7 parameters have schema descriptions (100% coverage). The description adds value by explaining the context of file_index (omitting to list files), privacy_mode override, and the interactive workflow. This goes beyond the schema's basic type and default information.

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 verb 'Transcribe' and the resource 'multiple audio/video files in a folder interactively, one file at a time.' It distinguishes itself from sibling tools like 'start_batch' for large unattended batches and 'transcribe_audio' for single files.

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?

Explicit guidance is given: 'For large unattended batch jobs, use start_batch instead.' It also explains when privacy_mode should be used and clarifies that already transcribed files are skipped. The description effectively sets context for when to invoke this tool.

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