Skip to main content
Glama

ask_conference

Run a multi-round brainstorming where several models debate a topic, building on or challenging each other, then produce a map of disagreement: converged points, crux, and what would change it.

Instructions

DIVERGENT, MULTI-ROUND — a brainstorming CONFERENCE where several models argue a topic TOGETHER over rounds, each reading the running transcript and building on (or pushing back against) what came before, then a rapporteur writes the MAP OF THE DISAGREEMENT (converged / the crux / what would change it). Unlike ask_council (models answer in isolation, then reconcile) the participants actually hear each other, so positions can move — use it for open-ended ideation and design exploration ('what should we build', 'ways to approach X'), where you want genuine divergence rather than one averaged answer. Pick the bench with models (from ['fable','opus','deepseek','minimax','glm','gemini','codex','grok','kimi'] plus any 'atlas:' / 'openrouter:' / 'ollama:' token); default is the available subset of fable/opus/deepseek/minimax/glm. rounds is 1–10 (default 3) and synthesizer writes the closing map (default 'fable'). When called with no models and the MCP client supports form elicitation, a NATIVE model picker pops up to choose the roster and topic (set interactive: false to skip it). Costs one model call per participant per round plus the synthesis, so it is heavier than a council — keep the bench and rounds modest. Same scope as ask: conceptual software/engineering ideation is in scope; direct offensive-security asks and non-software domains are refused. Aliases: 'm3' = minimax, 'gpt' = codex, 'opus5' = opus.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelsNoThe debater bench (2 or more). From ['fable','opus','deepseek','minimax','glm','gemini','codex','grok','kimi'] plus any 'ollama:<model>' / 'atlas:<id>' / 'openrouter:<id>' token. Omit to be offered a native picker (when the client supports elicitation), else it falls back to the available subset of fable/opus/deepseek/minimax/glm.
roundsNoHow many rounds of turns each participant takes (default 3, up to 10).
contextNoOptional code snippets, file paths, or structural context (shared by all participants).
sessionNoOptional coordination key for the cross-agent hub (`session_list` / `session_peek`). Reuse the same key across agents working the same decision so turns group together. Defaults to the tool name (`ask_council` / `ask_chain` / `ask_debate` / …) when omitted.
trustedNoOperator-authorized. When true, the prohibited-use denylist runs in log-only mode: security vocabulary in the question AND in `context` is audited but does not block. Use for legitimate security-engineering work (PoC analysis, CVE research, binary hardening review) where the ask genuinely needs security terms. Takes effect ONLY when the operator has set ASK_FABLE_ALLOW_TRUSTED (env or config); otherwise the flag is ignored and the denylist still applies.
questionNoThe topic or open question for the models to brainstorm and argue together.
context_refNoKey(s) of context saved with `context(op="write", …)` to pull in and prepend to `context` — paste a big context ONCE, reference it by key here. Missing keys are reported, not fatal.
interactiveNoWhen true and `models` is omitted, pop a native model picker if the MCP client supports form elicitation. Set false to skip it.
synthesizerNoModel that writes the closing map of the disagreement (default 'fable'; 'opus', 'codex', …).fable
attack_premiseNoAfter the blind round, name the premise every opening assumed and assign one participant to argue it is FALSE (two extra calls). This is the challenge nobody else will make, since agreeing on the premise is what lets the rest of the discussion happen. Needs 3+ seats and 2+ rounds; skipped otherwise.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.18.0
    • addedInput schema / properties / attack_premise
      Added value: +{
      +  "default": true,
      +  "description": "After the blind round, name the premise every opening assumed and assign one participant to argue it is FALSE (two extra calls). This is the challenge nobody else will make, since agreeing on the premise is what lets the rest of the discussion happen. Needs 3+ seats and 2+ rounds; skipped otherwise.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / context_ref / description
      Previous value: -"Key(s) of context saved with `context_write` to pull in and prepend to `context` — paste a big context ONCE, reference it by key here. Missing keys are reported, not fatal."New value: +"Key(s) of context saved with `context(op=\"write\", …)` to pull in and prepend to `context` — paste a big context ONCE, reference it by key here. Missing keys are reported, not fatal."
    • changedInput schema / properties / models / items / anyOf
      Previous value: -[
      -  {
      -    "enum": [
      -      "fable",
      -      "fable51",
      -      "opus",
      -      "opus48",
      -      "sonnet",
      -      "deepseek",
      -      "minimax",
      -      "glm",
      -      "gemini",
      -      "codex",
      -      "grok",
      -      "kimi",
      -      "claude-fable-5-1",
      -      "claude-opus-4-8",
      -      "claude-opus-5",
      -      "claude-sonnet-5",
      -      "fable-5.1",
      -      "fable-51",
      -      "fable5.1",
      -      "gpt",
      -      "m3",
      -      "opus-4.8",
      -      "opus-48",
      -      "opus-5",
      -      "opus4.8",
      -      "opus5",
      -      "sonnet-5",
      -      "sonnet5",
      -      "xai",
      -      "twin",
      -      "twin flame",
      -      "twin flames",
      -      "twin-flame",
      -      "twin-flames",
      -      "twin_flame",
      -      "twin_flames",
      -      "twinflame",
      -      "twinflames",
      -      "twins"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^ollama:.+",
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^atlas:.+",
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^openrouter:.+",
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^lmstudio:.+",
      -    "type": "string"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "fable",
      +      "fable51",
      +      "opus",
      +      "opus55",
      +      "opus5",
      +      "opus48",
      +      "sonnet",
      +      "deepseek",
      +      "minimax",
      +      "glm",
      +      "gemini",
      +      "codex",
      +      "grok",
      +      "kimi",
      +      "claude-fable-5-1",
      +      "claude-opus-4-8",
      +      "claude-opus-5",
      +      "claude-opus-5-5",
      +      "claude-sonnet-5",
      +      "fable-5.1",
      +      "fable-51",
      +      "fable5.1",
      +      "gpt",
      +      "m3",
      +      "opus-4.8",
      +      "opus-48",
      +      "opus-5",
      +      "opus-5.5",
      +      "opus-55",
      +      "opus4.8",
      +      "opus5.5",
      +      "sonnet-5",
      +      "sonnet5",
      +      "xai",
      +      "twin",
      +      "twin flame",
      +      "twin flames",
      +      "twin-flame",
      +      "twin-flames",
      +      "twin_flame",
      +      "twin_flames",
      +      "twinflame",
      +      "twinflames",
      +      "twins"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^ollama:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^atlas:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^openrouter:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^lmstudio:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^ali:.+",
      +    "type": "string"
      +  }
      +]
  2. Changed2 schema fields changedv0.16.0
    • changedInput schema / properties / models / items / anyOf
      Previous value: -[
      -  {
      -    "enum": [
      -      "fable",
      -      "fable51",
      -      "opus",
      -      "deepseek",
      -      "minimax",
      -      "glm",
      -      "gemini",
      -      "codex",
      -      "grok",
      -      "kimi",
      -      "claude-fable-5-1",
      -      "claude-opus-5",
      -      "fable-5.1",
      -      "fable-51",
      -      "fable5.1",
      -      "gpt",
      -      "m3",
      -      "opus-5",
      -      "opus5",
      -      "xai",
      -      "twin",
      -      "twin flame",
      -      "twin flames",
      -      "twin-flame",
      -      "twin-flames",
      -      "twin_flame",
      -      "twin_flames",
      -      "twinflame",
      -      "twinflames",
      -      "twins"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^ollama:.+",
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^atlas:.+",
      -    "type": "string"
      -  },
      -  {
      -    "pattern": "^openrouter:.+",
      -    "type": "string"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "fable",
      +      "fable51",
      +      "opus",
      +      "opus48",
      +      "sonnet",
      +      "deepseek",
      +      "minimax",
      +      "glm",
      +      "gemini",
      +      "codex",
      +      "grok",
      +      "kimi",
      +      "claude-fable-5-1",
      +      "claude-opus-4-8",
      +      "claude-opus-5",
      +      "claude-sonnet-5",
      +      "fable-5.1",
      +      "fable-51",
      +      "fable5.1",
      +      "gpt",
      +      "m3",
      +      "opus-4.8",
      +      "opus-48",
      +      "opus-5",
      +      "opus4.8",
      +      "opus5",
      +      "sonnet-5",
      +      "sonnet5",
      +      "xai",
      +      "twin",
      +      "twin flame",
      +      "twin flames",
      +      "twin-flame",
      +      "twin-flames",
      +      "twin_flame",
      +      "twin_flames",
      +      "twinflame",
      +      "twinflames",
      +      "twins"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^ollama:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^atlas:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^openrouter:.+",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^lmstudio:.+",
      +    "type": "string"
      +  }
      +]
    • addedInput schema / properties / trusted
      Added value: +{
      +  "default": false,
      +  "description": "Operator-authorized. When true, the prohibited-use denylist runs in log-only mode: security vocabulary in the question AND in `context` is audited but does not block. Use for legitimate security-engineering work (PoC analysis, CVE research, binary hardening review) where the ask genuinely needs security terms. Takes effect ONLY when the operator has set ASK_FABLE_ALLOW_TRUSTED (env or config); otherwise the flag is ignored and the denylist still applies.",
      +  "type": "boolean"
      +}
  3. Addedv0.14.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true. The description adds meaningful behavioral context: cost ('one model call per participant per round plus the synthesis'), interactive picker behavior, the `attack_premise` mechanics (two extra calls, requires 3+ seats and 2+ rounds), and alias handling. It does not contradict annotations and provides transparency beyond the schema flags.

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 description is long but densely informative, front-loading the core concept and differentiation. Every sentence serves a purpose: definition, contrast, usage, parameters, cost, scope, aliases. It is not padded; the length is justified by the tool's complexity. It could be slightly tighter, but it remains efficient.

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 most critical aspects: usage, parameters, costs, scope, aliases, and interactive behavior. It hints at the output format (MAP OF THE DISAGREEMENT) but does not fully describe its structure. It also lacks explicit error or fallback behaviors, but overall it is thorough enough for an agent to invoke 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 the baseline is 3, but the description adds value: it explains default bench behavior, alias mapping, the `attack_premise` preconditions, and the `interactive` picker interaction. It also clarifies that `context_ref` pulls pre-saved context and that missing keys are non-fatal. These details go beyond the schema descriptions.

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 'DIVERGENT, MULTI-ROUND — a brainstorming CONFERENCE where several models argue a topic TOGETHER over rounds' and clearly states the output (a MAP OF THE DISAGREEMENT). It explicitly differentiates from `ask_council` by contrasting the interaction model. The verb is specific ('conduct a conference'), the resource is the models, and it is unambiguous.

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?

The description explicitly states when to use it ('use it for open-ended ideation and design exploration') and contrasts it with `ask_council` ('models answer in isolation, then reconcile'). It also gives scope boundaries ('conceptual software/engineering ideation is in scope; direct offensive-security asks and non-software domains are refused'). This gives clear selection criteria.

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