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

Annotations only declare openWorldHint, so the description carries the load and does well: it discloses a real side effect (STT is auto-muted during injection so the agent doesn't hear itself), the billing behavior (covered by session deposit, no extra payment), and TTS fallback behavior with a warning on the reply. Missing only error/latency behavior to reach a 5.

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?

Front-loads the core action, then the two modes, then the side effect and cost note; every sentence contributes. It is somewhat dense (long clauses and parentheticals) but no sentence is filler.

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 6-parameter mutation-style tool with no output schema and minimal annotations, the description supplies the essential operational context: prerequisite session, mode selection, side effects, billing, and fallback voice behavior. Only return-value/error detail is thin, which is acceptable given no output schema.

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% and the schema already labels text as '(mode 1)' and audioBase64/encoding as '(mode 2)', including enum values and the voiceDescription fallback caveat. The description's mode framing adds little beyond that, so the baseline 3 applies.

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 and target ('Inject audio into an open Voice Bridge call') and then enumerates two distinct modes, so an agent knows immediately this is a live-call audio injection tool. It only implicitly distinguishes itself from siblings like text_to_speech or open_voice_bridge via the sessionId prerequisite, so differentiation is present but not spelled out.

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?

Clearly frames usage: it operates on an already-open call (via sessionId from open_voice_bridge) and routes the caller into mode 1 (text/TTS) or mode 2 (bring-your-own audio). It does not explicitly say when to prefer a sibling such as text_to_speech instead, so guidance is strong but not exhaustive.

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