Speak text on a live call

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

Annotations already declare destructive/not-idempotent/openWorld, and the description adds real context beyond them: that the target must be a live call, the TTS voice/language/SSML options, and the stop_speaking counterpart. It does not disclose queuing/serialization behavior or what happens to in-progress speech, so a 4 rather than 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-loaded with the core action and endpoint, then compact parameter hints, then the stop routing. The trailing semicolon-delimited clause list is dense but every element is actionable; minor clutter from repeating enum values already in the schema.

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 an 8-parameter, no-output-schema mutation tool, the description covers the primary flow and stopping but omits semantics for mix/loop/legs, any note on non-idempotent behavior or playback queuing, and error conditions such as a non-live call.

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 only 38%, and the description only echoes enum-level detail (voice WOMAN/MAN, language examples, type=ssml) while leaving mix, loop, and much of the behavior of legs unexplained. It adds moderate usage framing for SSML but does not compensate for the undocumented parameters.

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?

Specific verb+resource+scope: 'Read text aloud into a LIVE call with Vobiz text-to-speech', plus the underlying endpoint POST /Call/{uuid}/Speak/. This clearly separates it from sibling file-playback tools (play_audio) and from control tools like stop_speaking.

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?

States the live-call context and routes the agent to stop_speaking for terminating playback, which is the main alternative an agent needs. It stops short of explicit when-not guidance (e.g., using play_audio for prerecorded files, or behavior on ended calls).

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