KaiCalls

Send Kai Into a Meeting

join_meeting

Idempotent

Send Kai into a Zoom, Google Meet, Microsoft Teams or Webex meeting by its link. Kai joins under the agent name, takes notes, and emails the owner a summary when the meeting ends. If the meeting has a waiting room, the host must admit Kai. In the default listen mode it answers out loud when someone says its name and counts against the plan's monthly meeting minutes (a business whose plan includes none gets its first hour free, once); avatar mode joins with a talking video face and counts one avatar meeting. Mirrors POST /api/v1/meetings.

Input Schema

TableJSON Schema

Name	Required	Description
`mode`	No	'listen' (default): joins with a still camera tile and answers out loud when someone says its name. 'avatar': joins with a talking video face; counts as one avatar meeting (separate from meeting minutes; every business gets one free), stays on camera for the first 30 minutes, then continues voice-only and leaves at 60 minutes.
`agent_id`	No	Which agent joins (optional; defaults to the business's first agent).
`bot_name`	No	Name shown in the meeting and the name people say to get a reply (optional; defaults to the agent's name). Must be a short, speakable name.
`avatar_id`	No	Avatar mode only: which stock face to use (optional; an unknown id returns the list of valid ones).
`business_id`	No	Business ID (required when the token can access several businesses).
`meeting_url`	Yes	The meeting link, e.g. https://meet.google.com/abc-defg-hij or a zoom.us join link.
`instructions`	No	Context for this meeting only, e.g. "This is an onboarding call for a new customer; walk them through setup" (optional, up to 2000 characters).
`camera_image_url`	No	Public https link to a .jpg shown as the camera tile (optional).

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when success is false
`meeting`	No
`success`	Yes	Whether the tool completed successfully

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 17, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations declare a non-read, open-world, non-destructive, idempotent operation, but the description adds rich behavioral detail beyond them: note-taking, an email summary at end, host admission for waiting rooms, and plan-minute/avatar-meeting billing consequences. The billing implications in particular are non-obvious and valuable.

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?

The action, platforms and core behavior are front-loaded in the first sentence, and the remaining sentences cover prerequisites and billing. It is dense but every clause carries real information, with only mild redundancy against the schema's mode description.

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?

With an output schema present, return values need no explanation, and the description fully covers prerequisites (waiting room), modes, billing and the underlying API endpoint. Nothing needed to invoke it correctly is missing.

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 coverage is 100%, so the schema already documents all 8 parameters including the mode enum and defaults. The description's mode/billing text largely duplicates the schema's mode description and adds no syntax or format detail the schema lacks; baseline 3 applies.

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?

'Send Kai into a Zoom, Google Meet, Microsoft Teams or Webex meeting by its link' names a specific verb (join/send into) and resource (meeting) and covers supported platforms. It is trivially distinguishable from siblings like leave_meeting and get_meeting, which describe the opposite or a read operation.

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?

Usage is implied rather than stated: the agent can infer it joins a live meeting, and the waiting-room admission and billing notes give some operating context. But there is no explicit when-to-use guidance, no mention of alternatives (e.g., leave_meeting, get_meeting), and no exclusions.

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

All KaiCalls tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.