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

Beyond the minimal annotation (openWorldHint: true), the description adds key behaviors: STT is automatically muted during injection, and no additional payment is required (covered by session deposit). These details help the agent understand side effects and costs. It could mention error handling if the session is invalid, but overall it adds meaningful transparency.

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?

Four sentences with no wasted words. The first sentence states the primary action, the second explains the two modes, the third covers a behavioral detail (STT muting), and the fourth addresses payment. Every sentence serves a distinct purpose, and the description is front-loaded.

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 has 6 parameters (all described), no output schema, and a straightforward purpose, the description covers the essential aspects: modes, limitations (encoding), and behavioral context. It could mention asynchronous behavior or success indicators, but the current completeness is high enough for effective use.

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% with descriptive parameter comments. The description adds value by explaining the two interaction modes (text vs audio_base64+encoding), noting that mp3/opus are not yet wired (MVP), and clarifying that voiceDescription is free-form. This goes beyond the schema without repeating it.

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 begins with a clear verb+resource: 'Inject audio into an open Voice Bridge call.' It then details two distinct modes (TTS or audio_base64+encoding), which distinguishes it from sibling tools like text_to_speech (standalone TTS) or open_voice_bridge (session management). The purpose is immediately obvious and specific.

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 explains when to use this tool (to inject audio into an active call) and mentions that STT is automatically muted, implying appropriate context. It does not explicitly state when not to use it or list alternatives, but the context signals from sibling names and the clear two-mode design provide sufficient guidance. Minor lack of exclusions prevents a 5.

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