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

The description goes far beyond the openWorldHint annotation, detailing the real-world phone call behavior, privacy (transcripts in memory, GC after 30 min, audio never persisted), refund via LNURL-withdraw, Bitcoin Lightning payment, and the temporary unavailability. It also discloses that premium-rate and satellite ranges are refused, giving the agent essential safety and operational context.

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 dense but well-structured, front-loading the unavailability warning and then logically moving through purpose, usage, privacy, and payment. Some redundancy exists (e.g., 'same service and pricing' repeats later price info), but each section earns its place for such a complex tool. A slightly tighter rewrite could improve conciseness.

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 tool's complexity, no output schema, and the need to coordinate with sibling tools (voice_bridge_say, poll_voice_bridge, end_voice_bridge), the description is highly complete. However, it does not explicitly state what open_voice_bridge returns (e.g., a session ID or how to reference the session in subsequent calls), which is a notable omission for such a stateful, multi-step workflow.

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 100%, so the baseline is 3. The description adds valuable context by explaining the payment workflow ('Requires create_payment with toolName='voice_bridge_open'... Deposit is priced per destination... call create_payment for the exact figure') and restrictions, which enriches the meaning of paymentId and related fields beyond the schema alone.

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 purpose with a specific verb and resource: 'Open a Voice Bridge session: a live phone call where YOUR LLM is the brain.' It distinguishes itself from siblings like ai_call ('fully-managed agent-style calls') and place_call ('one-shot TTS broadcasts or IVR playback'), making the unique role unmistakable.

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?

Provides explicit when-to-use and when-not-to-use guidance with named alternatives: 'Use this when you want to keep your conversation context private and drive each turn yourself' and 'When NOT to use' lists ai_call, place_call, and cases where transcript polling adds no value. It also notes the current unavailability and directs to the HTTP endpoint or ai_call.

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