Loading ToolBench
Jambonz MCP server provides 3 focused, well-designed developer tools for a specialized telephony/voice platform. Strong naming and schema clarity, but description completeness varies. Tool count (3) is excellent for curation. Schema descriptions for get_jambonz_schema and get_sdk_example are truncated in the input but appear intentionally comprehensive. Overall demonstrates production-grade design intent with clear use cases for developer workflows.
Get the JSON Schema for a jambonz verb or component. Available: verb:agent, verb:alert, verb:answer, verb:conference, verb:config, verb:deepgram_s2s, verb:dequeue, verb:dial, verb:dialogflow, verb:dtmf, verb:dub, verb:elevenlabs_s2s, verb:enqueue, verb:gather, verb:google_s2s, verb:hangup, verb:leave, verb:listen, verb:llm, verb:message, verb:openai_s2s, verb:pause, verb:play, verb:redirect, verb:rest_dial, verb:s2s, verb:say, verb:sip-decline, verb:sip-refer, verb:sip-request, verb:stream, verb:tag, verb:transcribe, verb:ultravox_s2s, component:actionHook, component:actionHookDelayAction, component:amd, component:auth, component:bidirectionalAudio, component:fillerNoise, component:llm-base, component:recognizer-assemblyAiOptions, component:recognizer-awsOptions, component:recognizer-azureOptions, component:recognizer-cobaltOptions, component:recognizer-customOptions, component:recognizer-deepgramOptions, component:recognizer-elevenlabsOptions, component:recognizer-gladiaOptions, component:recognizer-googleOptions, component:recognizer-houndifyOptions, component:recognizer-ibmOptions, component:recognizer-nuanceOptions, component:recognizer-nvidiaOptions, component:recognizer-openaiOptions, component:recognizer-sonioxOptions, component:recognizer-speechmaticsOptions, component:recognizer-verbioOptions, component:recognizer, component:synthesizer, component:target, component:vad, callback:agent-turn, callback:amd, callback:call-status, callback:conference-status, callback:conference-wait, callback:conference, callback:dequeue, callback:dial-dtmf, callback:dial-hold, callback:dial-refer, callback:dial, callback:enqueue-wait, callback:enqueue, callback:gather-partial, callback:gather, callback:listen, callback:llm, callback:message, callback:play, callback:session-new, callback:session-reconnect, callback:session-redirect, callback:sip-refer-event, callback:sip-refer, callback:sip-request, callback:transcribe-translation, callback:transcribe, callback:tts-streaming-event, callback:verb-status, guide:bridged-call-patterns, guide:session-commands, guide:node-sdk
Get full source code for an SDK example. Available: agent, assemblyai-autogenerate-prompt, call-recording, deepgram-voice-agent, dial, echo, elevenlabs-voice-agent, hello-world, ivr-menu, listen-record, llm-streaming, openai-realtime, queue-with-hold, realtime-translator, retell-hosted, two-stage-dialer, ultravox-voice-agent, voice-agent
Description text truncation in get_jambonz_schema and get_sdk_example makes full enum list illegible - users cannot see all available options without calling the tool
get_jambonz_schema description is cut off mid-verb list ('verb:leav' likely incomplete) - prevents agents from knowing full schema availability upfront
get_sdk_example description truncates at 'two-stage-di' with incomplete schema JSON - list ends abruptly
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-04-24 | C | 62 | 2025-11-25 | v1 |
REQUIRED: call this before writing jambonz code. Returns the developer guide (verb model, transports, SDK API, patterns) and lists all available schemas.