Skip to main content
Glama
kaelorlabs

Smitline

by kaelorlabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Start a phone call or join a meeting

start_call

Places phone calls or joins video meetings for the user, conducts the conversation toward a defined objective, and returns a structured result.

Instructions

Place a phone call or join a video meeting for the user. Smitline talks with people in real time using GPT-Live and returns a structured result when the call ends. Write a complete brief: the goal, what to find out (questions), what may be agreed to, and what must not be shared. Pass what you and the user have been working on as context (summary, facts, and long details) so the assistant can answer questions like someone who knows the story. The user's profile (who they are, the people they know) is added automatically; keep it current with update_profile. If anything required is unknown, ask the user instead of guessing. For a first call to someone new, offer a rehearsal on the user's own phone. Returns immediately; then call wait_for_call with since: "" to follow the call live and supervise it. With canDo, people on the call can ask you for things; follow the call to answer them.

Input Schema

NameRequiredDescriptionDefault
toNoE.164 phone number such as +14155550142, or the meeting invite URL. Omit only for a rehearsal, which rings the user's own phone.
taskNoThe job several calls serve, such as getting quotes from ten roofers. Use the same id for each call in it.
toneNoHow to come across, such as "casual, he is a close friend". Defaults to matching the relationship.
canDoNoWhat you will do for the people on the call when they ask, such as "look things up in the repo and edit the docs". With it, the voice passes their requests to you (live.requests in wait_for_call) and you answer with reply_to_call_request; it declines anything else. Omit it and nobody can ask you for anything. Name only what you can do and the user would approve.
voiceNoGPT-Live voice name; see list_voices
notifyNo
recordNoPhone only: record this call in the user's phone account; the assistant tells the other person the call is recorded. Only when the user asks for a recording.
channelYesphone to place a call; meeting to join Zoom, Teams, or Google Meet
contactNoWho is being called, when the user's profile does not already know this number.
contextNoWhat you and the user have been working on that the other party may ask about. Text, or an object: summary (a few sentences), facts, decisions, openQuestions, and details (long reference material). The voice starts with a short version and looks details up when asked; it never recites them.
languageNoLanguage tag such as en or es
carryFromNoStart with short notes from earlier calls (at most 10). task: earlier calls in this brief's task; contact: earlier calls to the same number (phone only), or false to skip what the user switched on for that contact; calls: these call ids. Only carry what this call needs: the assistant may mention it to the other party, so do not carry one business's details to another unless the objective calls for it.
objectiveYesWhat the call must achieve, in one or two sentences
questionsNoWhat to find out on the call. The result answers each one.
rehearsalNoPhone only: practice on the user's own phone first, with the user playing the other side
afterHoursNoPhone only: call even though it is outside calling hours (8 AM to 9 PM) where the person is. Set only when the user confirms the person expects a call now.
maxMinutesNoPhone calls: at most 60 (default 10). Meetings: at most 240 (default 120).
mayAgreeToNoWhat the assistant may agree to without checking back, such as acceptable times or prices
onBehalfOfNoThe user's name, spoken in the opening: Hi, I'm calling on behalf of NAME about... Defaults to the name given at setup.
mustNotShareNoInformation the assistant must never share
successCriteriaNoHow to tell the call succeeded

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / canDo
      Added value: +{
+  "description": "What you will do for the people on the call when they ask, such as \"look things up in the repo and edit the docs\". With it, the voice passes their requests to you (live.requests in wait_for_call) and you answer with reply_to_call_request; it declines anything else. Omit it and nobody can ask you for anything. Name only what you can do and the user would approve.",
+  "maxLength": 500,
+  "type": "string"
+}
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag openWorld=true, non-idempotent and non-destructive, but the description adds genuinely non-obvious traits: the tool is asynchronous and returns at once, the profile is injected automatically, recording discloses to the other party, and after-hours calling is restricted. It does not describe the shape of the structured result, which matters since there is no output schema.

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?

Purpose and channel scope are front-loaded, then briefing guidance, then the follow-up flow. Every sentence is doing work, though it is dense at eight sentences and the 'Smitline talks with people in real time using GPT-Live' line is more branding than instruction.

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

Completeness4/5

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

For a 21-parameter, nested, asynchronous tool with no output schema, the description covers the call flow, the profile dependency, rehearsals, recording disclosure, and the handoff to wait_for_call. The one gap is what the 'structured result' actually contains, which the agent must discover by calling get_call.

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

Parameters4/5

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

Schema coverage is 95%, so the baseline is 3; the description earns a notch above by explaining how to compose the brief — objective, questions, mayAgreeTo, mustNotShare, and the summary/facts/details split for context — rather than restating field names. It adds intent-level guidance the schema's per-field strings do not fully convey.

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?

Opens with a specific verb+resource pair ('Place a phone call or join a video meeting for the user') and immediately names the agent behind it and the two channels. An agent can distinguish it from wait_for_call, get_call, or end_call without opening any schema.

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

Usage Guidelines5/5

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

Gives explicit routing: 'Returns immediately; then call wait_for_call with since: "" to follow the call live.' It also states prerequisites ('If anything required is unknown, ask the user instead of guessing') and a conditional alternative ('For a first call to someone new, offer a rehearsal'). When-to-use and when-to-do-something-else are both covered.

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