Skip to main content
Glama
ptaramona

Conduyt MCP Server

by ptaramona
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

conduyt_voice_drop

Place an outbound voice drop to a contact via Twilio with answering-machine detection, playing a voicemail recording to machines and ending calls quietly for humans.

Instructions

Place a voice drop to a contact (POST /api/v1/calls/voice-drop): an outbound Twilio call with answering-machine detection that plays one of the account's Voicemail Drop recordings (Settings → Twilio → Voicemail Drop; names from conduyt_sms_transports voiceDrop.recordings) when a machine answers, and hangs up quietly when a person answers unless onHuman is play. Governed like a call: calls-tier consent (a texting STOP does not block it, a DNC or litigator row does), the account's calling hours, one live call per lead. Placed from your own Twilio line (else the account number) unless fromNumber names a number the account owns. Returns 202 with the Call row; the outcome lands on it through the voice webhooks (disposition voicemail_drop = played to a machine, voice_drop_human = a person answered, voice_drop_live = played to a person, voice_drop_fax; status no-answer/busy when nobody picked up). Refusals carry a code (dnc, litigator, calling_window, active_call, missing_phone, voice_drop_recording_missing, voice_drop_not_configured); 429 and 502 are safe to retry. Requires dialer:create.

Input Schema

NameRequiredDescriptionDefault
onHumanNoWhen a person answers: hang_up (default) ends the call quietly; play plays the recording anyway
contactIdYesContact UUID — the drop calls the contact's primary number
recordingNoA Voicemail Drop template name (see conduyt_sms_transports voiceDrop.recordings.templates); omit for the default recording
fromNumberNoCaller ID the account owns (the account number or an active rep's line, E.164); omit for your own line

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.71.0

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations present, the description carries the full burden and does so thoroughly: it discloses the 202 response with a Call row, the fact that outcomes arrive asynchronously via voice webhooks (naming each disposition), the consent/DNC/calling-hours/live-call gating, the retry-safe 429/502 statuses, and the required dialer:create permission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with verb, resource, and endpoint, and nearly every clause adds operational value (governance, return shape, refusal codes). It is dense but single-paragraph and slightly overstuffed, packing error codes and webhook dispositions into one unwieldy block.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description compensates fully: it explains the return value, the asynchronous outcome lifecycle, every refusal code, retry behavior, and the authorization requirement. An agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and all four parameters are already documented in the schema, so the baseline is 3. The description adds only marginal semantics, mainly the caller-ID resolution order (own Twilio line, else account number, unless fromNumber names an owned number), and repeats the onHuman play/hang_up distinction.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (place a voice drop), names the endpoint, and immediately defines the mechanism: an outbound Twilio call with answering-machine detection. It clearly distinguishes the drop from a live conversation by describing machine-answer vs. person-answer behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context in which to use it (leaving a pre-recorded voicemail on a contact) is implied clearly, but there is no explicit when-to-use/when-not statement and no named alternative such as placing a normal call or using a sequence/drip. The reference to conduyt_sms_transports is for configuration lookup, not for choosing between tools.

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

Deploy Server

Other Tools