start_transcription

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

With no annotations provided, the description carries full behavioral burden and excels. It discloses real-time chunked transcription, auto-pause conditions (32s silence, 30 min no interaction), defines which actions count as interaction, and instructs on detecting pause via isPaused: true and resuming. This gives the agent critical operational knowledge beyond the schema.

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 moderately long but well-structured with 'IMPORTANT' and 'SAFETY FEATURES' sections. Every sentence provides actionable information, though it could be tightened without losing meaning. It's not overly verbose for the complexity it covers.

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?

Given the complexity (long-running live transcription) and lack of output schema, the description is largely complete: it covers monitoring, safety, and follow-up actions. However, it omits explicit instruction on how to fully end the session (e.g., using stop_transcription), which is only inferable from sibling tool names.

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 description coverage is 100%, so the baseline is 3. The tool description does not add any new parameter semantics; it omits mention of outputFile, inputDevice, or chunkSeconds. However, the schema's own descriptions are complete, so no compensation is needed.

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: 'Start capturing and transcribing system audio in real-time using OpenAI Whisper.' It specifies the verb (start), resource (system audio), and method (OpenAI Whisper), and distinguishes it from sibling tools like pause_transcription and stop_transcription by positioning it as the entry point for the transcription workflow.

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?

The description implies usage as the initial step in a transcription session but does not explicitly contrast it with alternatives. It provides clear post-start guidance ('periodically check get_status every 30-60 seconds') and explains safety features, but it does not state when to use this tool vs. stopping or cleaning up, leaving that to inference from sibling tool names.

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