Skip to main content
Glama

start_local_meeting

Starts a local agent meeting using the Claude CLI and returns a meeting ID for follow-up messages, so you can hold cost-conscious lengthy discussions without API credits.

Instructions

Start a LOCAL meeting with an agent using the installed Claude CLI. This uses your Claude Pro/Max subscription instead of API credits. Returns a meeting ID for follow-up messages. Ideal for cost-conscious lengthy conversations. Pass mode: "debate" to have the agent stress-test your agenda as a challenger instead. Pass prototype: true to have the agent show its proposals as ephemeral prototypes that you assess.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent": "<agent>",
      "agenda": "<agenda>"
    },
    "name": "start_local_meeting"
  }
}

Input Schema

NameRequiredDescriptionDefault
duelNoOptional duel id (duel-...) from ROUNDTABLE_HOME/duels to make the focus of this session: a scrubbed, size-capped brief of the duel (teams, artifacts, verdicts, tally, dissents) is added to the context every participant sees, as untrusted content to discuss. An unknown or invalid id is an error before any provider call.
modeNodebate: the agent acts as a challenger and stress-tests your agenda instead of helping execute it. Default: standard.
agentYesAgent identifier or path to prompt file. Examples: "cfo", "fpa", "product"
agendaYesThe topic, question, or task to discuss with the agent.
publicNoDefault false. Only set true when the human explicitly asks for a public session. When true, the whole session is posted live to the configured public channel and is world-readable: the topic/agenda, every agent reply, every message you send with say/nudge, and the summary. The context argument is never posted, but agents may paraphrase it in their replies, so keep context generic. Never include personal information, credentials, or private code anywhere in a public session. The result includes public.url so the human can watch live.
contextNoOptional additional context, document content, or data to share.
prototypeNoDefault false. Prototype mode: agents show proposals as ephemeral artifacts — a scaled-down page shown in a sandboxed frame on a localhost board, the code/IaC that would produce the proposal (never executed), a Mermaid diagram, or a text draft — and the other participants (in meetings: you) give verdicts; the proposer then revises, scraps or shortlists. Results include a prototypes block with the board URL: show it to the human. Prototypes are destroyed as soon as assessment completes. Do not relay the human's feedback on prototypes into the session until it ends; end_* lists outcomes and the shortlist for the human. Combinable with public (public posts get code, diagram links and screenshots of web prototypes, never the localhost board). Not supported with mode conversation.
page_checkNoCheck web prototypes in local headless Chrome when available (default true).
duel_sourceNoDefault true; only with duel. The duel brief is resent on every turn to every participant (a full brief can be about 20k tokens per turn). Set false to leave out artifact file contents and keep titles, file names and sizes, verdicts, tally and dissents.
debate_focusNoOptional: what the challenge should concentrate on (only used with mode debate).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv2.0.0
    • addedInput schema / properties / debate_focus
      Added value: +{
      +  "description": "Optional: what the challenge should concentrate on (only used with mode debate).",
      +  "type": "string"
      +}
    • addedInput schema / properties / duel
      Added value: +{
      +  "description": "Optional duel id (duel-...) from ROUNDTABLE_HOME/duels to make the focus of this session: a scrubbed, size-capped brief of the duel (teams, artifacts, verdicts, tally, dissents) is added to the context every participant sees, as untrusted content to discuss. An unknown or invalid id is an error before any provider call.",
      +  "type": "string"
      +}
    • addedInput schema / properties / duel_source
      Added value: +{
      +  "description": "Default true; only with duel. The duel brief is resent on every turn to every participant (a full brief can be about 20k tokens per turn). Set false to leave out artifact file contents and keep titles, file names and sizes, verdicts, tally and dissents.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "debate: the agent acts as a challenger and stress-tests your agenda instead of helping execute it. Default: standard.",
      +  "enum": [
      +    "standard",
      +    "debate"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / page_check
      Added value: +{
      +  "description": "Check web prototypes in local headless Chrome when available (default true).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / prototype
      Added value: +{
      +  "description": "Default false. Prototype mode: agents show proposals as ephemeral artifacts — a scaled-down page shown in a sandboxed frame on a localhost board, the code/IaC that would produce the proposal (never executed), a Mermaid diagram, or a text draft — and the other participants (in meetings: you) give verdicts; the proposer then revises, scraps or shortlists. Results include a prototypes block with the board URL: show it to the human. Prototypes are destroyed as soon as assessment completes. Do not relay the human's feedback on prototypes into the session until it ends; end_* lists outcomes and the shortlist for the human. Combinable with public (public posts get code, diagram links and screenshots of web prototypes, never the localhost board). Not supported with mode conversation.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / public
      Added value: +{
      +  "description": "Default false. Only set true when the human explicitly asks for a public session. When true, the whole session is posted live to the configured public channel and is world-readable: the topic/agenda, every agent reply, every message you send with say/nudge, and the summary. The context argument is never posted, but agents may paraphrase it in their replies, so keep context generic. Never include personal information, credentials, or private code anywhere in a public session. The result includes public.url so the human can watch live.",
      +  "type": "boolean"
      +}
  2. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses billing implications (subscription vs API credits), the return contract (a meeting ID for follow-up messages), and two distinct behavioral modes with their own semantics. The richest behavioral detail — public posting being world-readable, prototype destruction on assessment, and the ~20k token per-turn duel brief — lives in the parameter descriptions rather than the top-level description, which leaves the headline text thinner than it could be.

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

Conciseness5/5

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

Four sentences, each earning its place: what it does, how it is funded, what it returns, and when to prefer it. The cost-relevant distinguishing fact is front-loaded in sentence two, and the two mode hints are compact pointers rather than redundant schema dumps.

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 10-parameter tool with no output schema, the description covers purpose, funding model, return value (meeting ID), and two major modes, with the remaining parameters fully covered by the schema. The one gap is that the top-level description never warns that a public session is world-readable, leaving that critical safety note buried in a parameter description.

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%, so all ten parameters are already well documented in the schema, and the description's parameter notes (mode: debate, prototype: true) restate what the schema says. Baseline 3 applies because the description adds little meaning beyond what structured fields already provide.

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?

The description opens with a specific verb+resource ("Start a LOCAL meeting with an agent") and immediately distinguishes this variant from its siblings by naming the execution path: the installed Claude CLI funded by a Pro/Max subscription rather than API credits. An agent can tell this apart from a cloud/API meeting starter without inspecting either schema.

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?

It gives a clear selection rationale for this tool in general ("Ideal for cost-conscious lengthy conversations") and inline guidance for two parameters (mode: "debate" to stress-test an agenda, prototype: true for ephemeral proposals). It never names start_meeting or the other siblings as the alternative to pick when cost is not a concern, so the routing is implied rather than explicit.

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