Skip to main content
Glama

show_conflicts

Identify disagreements among AI models on technology choices, approach, and assumptions from Round 1 of a multi-model planning session.

Instructions

Show all points where models disagreed in Round 1 — technology choices, approach, and assumption conflicts

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNameNoYour model name (optional)

Implementation Reference

  • src/server.ts:204-216 (registration)
    Registration of the 'show_conflicts' tool on the MCP server. Defines the schema (optional modelName) and the handler that calls executeConflicts().
    // ─── show_conflicts ───────────────────────────────────────────────
    server.tool(
      "show_conflicts",
      "Show all points where models disagreed in Round 1 — technology choices, approach, and assumption conflicts",
      {
        modelName: z.string().optional().describe("Your model name (optional)"),
      },
      async (params, extra) => {
        const identity = detectCaller(server.server.getClientVersion(), params.modelName);
        const formatted = await executeConflicts(projectRoot, identity);
        return { content: [{ type: "text", text: formatted }] };
      }
    );
  • The executeConflicts function that orchestrates conflict detection. Reads round 1 plans, calls detectConflicts and formatConflicts from the engine, logs the action, and returns the formatted result.
    export async function executeConflicts(
      projectRoot: string,
      identity: CallerIdentity
    ): Promise<string> {
      const round1Plans = await readPlansByRound(projectRoot, "round1");
    
      if (round1Plans.length < 2) {
        return `Need at least 2 Round 1 plans to detect conflicts. Currently have ${round1Plans.length}.`;
      }
    
      const conflicts = detectConflicts(round1Plans);
      const formatted = formatConflicts(conflicts, "Round 1");
    
      await logAction(
        projectRoot,
        identity.cliTool,
        identity.modelName,
        "conflicts",
        `Analyzed conflicts: ${conflicts.length} found across ${round1Plans.length} plans`
      );
    
      return formatted;
    }
  • Input schema for show_conflicts: optional modelName string parameter.
    {
      modelName: z.string().optional().describe("Your model name (optional)"),
  • Core conflict detection logic: compares keyword-based technology choices across plans to find disagreements.
    export function detectConflicts(plans: PlanFile[]): Conflict[] {
      if (plans.length < 2) return [];
    
      const conflicts: Conflict[] = [];
    
      // Collect mentions per plan
      const planMentions = plans.map((plan) => ({
        identifier: `${plan.cliTool}-${plan.modelName}`,
        mentions: detectMentions(plan.content, TECH_CATEGORIES),
      }));
    
      // Check each category for disagreement
      for (const category of TECH_CATEGORIES) {
        const positions: Record<string, string> = {};
        const allChoices = new Set<string>();
    
        for (const pm of planMentions) {
          const mentions = pm.mentions.get(category.name);
          if (mentions && mentions.length > 0) {
            const choice = mentions.join(" + ");
            positions[pm.identifier] = choice;
            allChoices.add(choice);
          }
        }
    
        // Conflict only if 2+ models mentioned this category AND they disagree
        const modelsThatMentioned = Object.keys(positions);
        if (modelsThatMentioned.length >= 2 && allChoices.size >= 2) {
          // Count votes per choice
          const voteCounts = new Map<string, number>();
          for (const choice of Object.values(positions)) {
            voteCounts.set(choice, (voteCounts.get(choice) ?? 0) + 1);
          }
    
          // Build summary
          const sortedChoices = [...voteCounts.entries()].sort((a, b) => b[1] - a[1]);
          const summary = sortedChoices
            .map(([choice, count]) => `${count} model(s) prefer ${choice}`)
            .join(", ");
    
          conflicts.push({
            category: category.name,
            positions,
            summary,
          });
        }
      }
    
      return conflicts;
    }
  • Formats detected conflicts into a human-readable string for display.
    export function formatConflicts(conflicts: Conflict[], round: string): string {
      if (conflicts.length === 0) {
        return `✅ No conflicts detected across ${round} plans. All models are in agreement on technology choices.`;
      }
    
      const lines: string[] = [];
      lines.push(`CONFLICTS DETECTED — ${round}`);
      lines.push("");
    
      conflicts.forEach((conflict, index) => {
        lines.push(`[CONFLICT ${index + 1}] ${conflict.category}`);
        for (const [model, position] of Object.entries(conflict.positions)) {
          lines.push(`  ${model.padEnd(28)} ${position}`);
        }
        lines.push(`  → ${conflict.summary}`);
        lines.push("");
      });
    
      lines.push("These conflicts will be surfaced to the Final round model for resolution.");
    
      return lines.join("\n");
    }
Behavior2/5

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

With no annotations, the description carries full burden for behavioral disclosure. It implies a read-only lookup but does not state whether prior execution of Round 1 is required, or if there are any side effects. Minimal transparency.

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 a single sentence that efficiently conveys the purpose. It is front-loaded and contains no unnecessary words.

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 simple tool with one optional parameter and no output schema, the description is nearly complete. It specifies the scope (Round 1) and types of conflicts. Minor gap: could mention output format or list nature.

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% for the single optional parameter 'modelName'. The tool description adds no extra meaning; it is baseline adequate given the schema already documents the parameter.

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 shows points of disagreement from Round 1, specifying types (technology choices, approach, assumption conflicts). It distinguishes from siblings like 'show_agree' and 'show_diff' by its focus on disagreements in a specific round.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like 'show_agree' or 'show_diff'. There is no mention of prerequisites or contextual usage.

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/IMAFDI/polyplan-mcp'

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