Start an audio stream on a live call

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

The annotations already flag the operation as destructive and open-world, but the description adds substantial context: audio is sent to an external server, service_url must be wss:// on an approved host, confirm gates the action, and bidirectional requires audio_track inbound. It also discloses the return value and content_type formats, giving the agent actionable behavioral detail.

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?

A single dense paragraph front-loads the purpose and covers necessary constraints without obvious filler. It could be more scannable given ten parameters and multiple safety caveats, but the length is largely justified.

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 destructive, open-world streaming tool with ten parameters and no output schema, the description covers purpose, use cases, safety prerequisites, parameter interactions, and the returned stream_id. No critical invocation context is missing.

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 90%, so nearly all parameters are already documented. The description restates the key constraints (wss/approved host, bidirectional/audio_track dependency, content_type options, confirm approval) but adds little parameter meaning beyond the schema; its main extra detail, the stream_id return, is output rather than parameter semantics.

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 (fork), resource (live Vobiz call audio), destination (WebSocket server), and timing (near real time), with the exact endpoint. It also names example use cases and notes the returned stream_id for get_audio_stream / stop_audio_stream, distinguishing it from sibling stream-management tools.

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?

Gives clear context with example scenarios (live transcription, AI voice agent) and a critical usage prerequisite: confirm: true after user approval. It does not explicitly say when not to use the tool or contrast it with alternatives like start_recording or play_audio, so it stops short of full routing guidance.

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