WebinarIgnition

Start a webinar

wi_start_webinar

Opens a new webinar conversation and returns the first question with tappable options. No sign-in and no setup. Take it when a host wants to begin, for example "I want to run a webinar about my coaching, where do we start?" It creates a session on the connector and returns a session id. Nothing is written to a WordPress site, nothing is published and no email goes out. You can pass what the host just said and what you already know about topic, audience, offer and tone, then the conversation opens there instead of at an empty menu. Words hosts use: start a webinar, begin, first webinar, no setup

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "wi_start_webinar"
  }
}

Input Schema

Name	Required	Description	Default
`focus`	No	what it should be about.
`has_wi`	No	true when WebinarIgnition is already installed on the host's site.
`language`	No	The language the host writes in.	de
`situation`	No	Only with this call or this call: what the host just said, in their own words. On this call this also starts a real conversation (seeded with known_facts) instead of only showing the menu — use it when the host already wrote something about their webinar.
`known_facts`	No	What the host already said about the webinar: topic, audience, offer, tone, date. Send it on the FIRST call (this call or this call) so the conversation does not ask again what is already known. Later calls keep it in the session and do not need it again.
`has_wordpress`	No	true when the host already has a WordPress site. Reist als Fluss-Signal mit: ohne es gilt der Standardweg (der Host hat vermutlich WordPress). Mit false wird der Verbinden-Schritt in der Strecke uebersprungen.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

changedInput schema / properties / known_facts / description

Previous value: -"Everything you already know — send it every turn so nothing is lost on a restart. On the FIRST call (this call or this call) this is how a chat/assistant hands over what it already learned about the host (topic, audience, offer, style/tone) instead of making them repeat it."New value: +"What the host already said about the webinar: topic, audience, offer, tone, date. Send it on the FIRST call (this call or this call) so the conversation does not ask again what is already known. Later calls keep it in the session and do not need it again."

AddedOct 19, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations declare a non-read-only, open-world, non-idempotent call, and the description adds real context beyond that: it says a session is created on the connector, a session id is returned, and explicitly that nothing is written to a WordPress site, published, or emailed. That side-effect scoping is exactly what an agent needs before invoking a state-creating tool.

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 the core action and the side-effect disclaimer, and the example is well placed. It is somewhat over-long: "No sign-in and no setup" is restated later, and the trailing keyword list "Words hosts use: start a webinar, begin, first webinar, no setup" duplicates earlier content.

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?

An output schema exists, so return values need not be explained, and the description covers the remaining essentials: trigger, side effects, session creation, and how to seed the first turn. For a six-parameter entry-point tool with all-optional parameters this leaves nothing an agent needs missing.

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 100%, so the baseline is 3, but the description adds behavioral meaning the schema lacks: passing the host's own words plus known topic/audience/offer/tone makes the conversation open there "instead of at an empty menu," and that known_facts prevents re-asking. It does not clarify the focus enum or has_wi/has_wordpress interaction, so it is not a full 5.

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

Purpose4/5

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

States a concrete verb and resource: "Opens a new webinar conversation and returns the first question with tappable options," and adds that it "creates a session on the connector and returns a session id." That is clearly distinct from the wi_change_*/wi_get_* siblings, but it never names wi_continue_webinar or wi_get_setup_plan, which are the nearest alternatives, so the differentiation is implied rather than explicit.

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

Usage Guidelines4/5

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

Provides an explicit trigger ("Take it when a host wants to begin") with a realistic utterance example and a list of host phrasings, which is strong positive routing. It stops short of stating when NOT to use it or naming the tool to use instead when a session already exists, so there are no exclusions.

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

All WebinarIgnition 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.