Skip to main content
Glama

board_convene_session

Start a governed deliberation session for a charter. AI models with roles debate the topic and return a session_id to retrieve results.

Instructions

Convene a governed deliberation session for a charter. Each seat (AI model with a specific role) deliberates on the topic according to the charter's mode (parallel/chain/adversarial/roundtable/auto). Returns a session_id — use board_get_session to retrieve the output once complete. Typical runtime: 30–120 seconds depending on seat count and mode.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
institution_idYesInstitution ID
charter_idYesCharter ID of the board or committee to convene
topicYesThe question, decision, or matter to deliberate on. Be specific — this is what every seat will reason about.
contextNoAdditional background context, documents, or data to inject into all seat prompts

Implementation Reference

  • The handler function for the board_convene_session tool. Calls the backend API POST /api/institution/{institution_id}/charter/{charter_id}/convene with topic and context, then returns the session_id and status.
      async (args) => {
        try {
          const data = await apiCall(
            `/api/institution/${args.institution_id}/charter/${args.charter_id}/convene`,
            'POST',
            {
              topic:       args.topic,
              context:     args.context,
              triggeredBy: 'mcp-client',
            }
          ) as any;
    
          return {
            content: [{ type: 'text' as const, text: JSON.stringify({
              session_id:     data.sessionId || data.session_id,
              charter_id:     args.charter_id,
              institution_id: args.institution_id,
              topic:          args.topic,
              status:         data.status || 'running',
              message:        data.message || 'Session convened — deliberation in progress',
              next_step:      `Call board_get_session with session_id "${data.sessionId || data.session_id}" to retrieve the deliberation output. Sessions typically complete in 30–90 seconds.`,
            }, null, 2) }],
          };
        } catch (err: unknown) {
          return boardErrorResponse(err);
        }
      }
    );
  • Input schema for board_convene_session: required institution_id, charter_id, topic; optional context string.
    {
      institution_id: z.string().describe('Institution ID'),
      charter_id:     z.string().describe('Charter ID of the board or committee to convene'),
      topic:          z.string().describe('The question, decision, or matter to deliberate on. Be specific — this is what every seat will reason about.'),
      context:        z.string().optional().describe('Additional background context, documents, or data to inject into all seat prompts'),
    },
  • Registration of the tool via server.tool('board_convene_session', ...) with description, schema, metadata flags, and handler.
    server.tool(
      'board_convene_session',
      'Convene a governed deliberation session for a charter. Each seat (AI model with a specific role) deliberates on the topic according to the charter\'s mode (parallel/chain/adversarial/roundtable/auto). Returns a session_id — use board_get_session to retrieve the output once complete. Typical runtime: 30–120 seconds depending on seat count and mode.',
      {
        institution_id: z.string().describe('Institution ID'),
        charter_id:     z.string().describe('Charter ID of the board or committee to convene'),
        topic:          z.string().describe('The question, decision, or matter to deliberate on. Be specific — this is what every seat will reason about.'),
        context:        z.string().optional().describe('Additional background context, documents, or data to inject into all seat prompts'),
      },
      { title: 'Convene Governed Session', readOnlyHint: false, idempotentHint: false, destructiveHint: false, openWorldHint: false },
      async (args) => {
        try {
          const data = await apiCall(
            `/api/institution/${args.institution_id}/charter/${args.charter_id}/convene`,
            'POST',
            {
              topic:       args.topic,
              context:     args.context,
              triggeredBy: 'mcp-client',
            }
          ) as any;
    
          return {
            content: [{ type: 'text' as const, text: JSON.stringify({
              session_id:     data.sessionId || data.session_id,
              charter_id:     args.charter_id,
              institution_id: args.institution_id,
              topic:          args.topic,
              status:         data.status || 'running',
              message:        data.message || 'Session convened — deliberation in progress',
              next_step:      `Call board_get_session with session_id "${data.sessionId || data.session_id}" to retrieve the deliberation output. Sessions typically complete in 30–90 seconds.`,
            }, null, 2) }],
          };
        } catch (err: unknown) {
          return boardErrorResponse(err);
        }
      }
    );
  • Registration of registerInstitutionTools in the TENANT tier tool registry, which includes board_convene_session as part of the board tools group.
    { tier: 'tenant', register: (server, _engine) => registerInstitutionTools(server), description: 'board (list_institutions, list_charters, convene_session, get_session, install_kit)' },
  • Onboarding config listing board_convene_session under the 'Reasoning' category for client configuration.
    | Reasoning | chain_of_reasoning, board_convene_session, board_search_precedent |
    | Colony | agent_citizenship_status, agent_rights, colony_health, colony_suggestion |
    | Phoenix Recovery | phoenix_snapshot, phoenix_verify_integrity, phoenix_recovery_health |
    | Value Metrics | record_value_metric, record_governance_event, generate_impact_report |
    | SRT | srt_run_watchdog, srt_diagnose, srt_approve_repair, srt_generate_postmortem |
Behavior4/5

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

Annotations indicate readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds behavioral context: it creates a session (non-destructive), takes time, and returns a session_id. It does not contradict any annotations and provides valuable runtime expectations.

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?

The description is concise, consisting of two sentences with no extraneous information. It front-loads the core action and provides essential details (runtime, output retrieval) efficiently. Every sentence earns its place.

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?

The tool has no output schema, but the description compensates by stating it returns a session_id and directing users to board_get_session for outputs. Combined with the detailed parameter descriptions and annotations, the description provides sufficient context for an agent to use the tool correctly.

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 parameters are well-documented in the schema. The description adds semantic value by elaborating on the 'topic' parameter ('Be specific — this is what every seat will reason about') and explaining the 'context' parameter. This enhances an agent's understanding beyond the schema.

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 clearly states the tool's purpose: convene a governed deliberation session for a charter. It explains the concept of seats and modes, and distinguishes itself from the sibling tool board_get_session, which retrieves outputs. The specific verb 'convene' and resource 'session' are well-defined.

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?

The description provides clear usage guidance: it explains the typical runtime (30–120 seconds) and directs users to board_get_session for retrieving results. However, it does not explicitly state when not to use this tool or list alternative tools beyond retrieval. Still, the context is sufficient for an agent to decide.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knowledgepa3/gia-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server