transcribe_to_labels

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

With no annotations, the description carries the full burden. It discloses experimental status, asynchronous behavior (returns job_id), language auto-detection pitfalls, retry behavior, and prerequisite cleanup. It could additionally specify whether existing labels are overwritten, but it adequately warns about cleanup requirements.

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 longer than average but each section earns its place: purpose, background behavior, language caveats, retry guidance, and cleanup steps. It is front-loaded with the main action and organized, though the language-detection warning could be tightened without losing value.

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 tool is complex (experimental, asynchronous, language-sensitive) and has no output schema, so the description must explain return values and follow-up actions. It does so via job_id and monitoring instructions. It also covers the setup requirement and retry strategy. Minor gaps: no detail on label track naming or whether the project is modified in place, but overall it is thorough.

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?

The input schema has no descriptions (0% coverage), but the description's 'Args' section explains each parameter in detail: model_size with enumerated values, language as ISO code or None, and task with transcribe/translate semantics. This fully compensates for the schema gap.

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 tool's function: 'Transcribe audio and add Audacity labels at each segment timestamp.' This specifies the verb (transcribe), resource (audio), and output (labels at timestamps), distinguishing it from sibling tools like transcribe_to_file and transcribe_selection.

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 provided: background execution with job_id and monitoring via check_transcription_status, when to pass language explicitly, when to use task='translate', retry with this same tool, and how to clear existing labels with track_select and track_remove. This covers both when to use and what not to use.

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