Skip to main content
Glama

twining_reconsider

Flag decisions for reconsideration by setting them to provisional status, posting warnings with impact analysis to coordinate agent actions.

Instructions

Flag a decision for reconsideration. Sets active decisions to provisional status and posts a warning to the blackboard with downstream impact analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
decision_idYesID of the decision to reconsider
new_contextYesNew context or reason for reconsideration
agent_idNoID of the agent requesting reconsideration

Implementation Reference

  • The business logic for 'twining_reconsider' which marks a decision as provisional and warns about downstream impacts.
    async reconsider(
      decisionId: string,
      newContext: string,
      agentId?: string,
    ): Promise<{ flagged: boolean; decision_summary: string }> {
      const decision = await this.decisionStore.get(decisionId);
      if (!decision) {
        throw new TwiningError(
          `Decision not found: ${decisionId}`,
          "NOT_FOUND",
        );
      }
    
      let flagged = false;
      if (decision.status === "active") {
        await this.decisionStore.updateStatus(decisionId, "provisional");
        flagged = true;
      }
    
      // Check for downstream dependents
      const index = await this.decisionStore.getIndex();
      const downstreamIds: string[] = [];
      for (const entry of index) {
        const d = await this.decisionStore.get(entry.id);
        if (d && d.depends_on.includes(decisionId)) {
          downstreamIds.push(d.id);
        }
      }
    
      let detail = newContext;
      if (downstreamIds.length > 0) {
        detail += `\nNote: ${downstreamIds.length} downstream decisions may be affected: ${downstreamIds.join(", ")}`;
      }
    
      // Post warning to blackboard
      await this.blackboardEngine.post({
        entry_type: "warning",
        summary: `Reconsideration flagged: ${decision.summary}`.slice(0, 200),
        detail,
        tags: [decision.domain],
        scope: decision.scope,
        agent_id: agentId ?? "main",
      });
    
      // Auto-populate graph with challenged relation
      if (this.graphPopulator) {
        await this.graphPopulator.onChallenge(agentId ?? "main", decisionId, "reconsider");
      }
    
      return { flagged, decision_summary: decision.summary };
    }
  • Registration of the 'twining_reconsider' MCP tool.
    // twining_reconsider — Flag a decision for reconsideration
    server.registerTool(
      "twining_reconsider",
      {
        description:
          "Flag a decision for reconsideration. Sets active decisions to provisional status and posts a warning to the blackboard with downstream impact analysis.",
        inputSchema: {
          decision_id: z.string().describe("ID of the decision to reconsider"),
          new_context: z
            .string()
            .describe("New context or reason for reconsideration"),
          agent_id: z
            .string()
            .optional()
            .describe("ID of the agent requesting reconsideration"),
        },
      },
      async (args) => {
        try {
          const result = await engine.reconsider(
            args.decision_id,
            args.new_context,
            args.agent_id,
          );
          return toolResult(result);
        } catch (e) {
          if (e instanceof TwiningError) {
            return toolError(e.message, e.code);
          }
          return toolError(
            e instanceof Error ? e.message : "Unknown error",
            "INTERNAL_ERROR",
          );
        }
      },
    );
Behavior3/5

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

With no annotations, the description carries the full burden and discloses key behavioral traits: it changes decision status to provisional and posts a warning with impact analysis, indicating a mutation with downstream effects. However, it lacks details on permissions, reversibility, or rate limits, leaving gaps for a tool with significant impact.

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 front-loaded and concise, using two efficient sentences that directly explain the tool's actions without waste. Every word contributes to understanding the purpose and effects.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a mutation tool with no annotations or output schema, the description is moderately complete: it covers the core action and effects but lacks details on return values, error handling, or full behavioral context, making it adequate but with clear gaps.

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 the schema already documents all three parameters. The description adds no additional meaning beyond implying that 'new_context' triggers the reconsideration, but it doesn't elaborate on format or constraints, meeting the baseline for high schema coverage.

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 with specific verbs ('flag', 'sets', 'posts') and resources ('decision', 'provisional status', 'warning to the blackboard'), distinguishing it from siblings like twining_acknowledge or twining_dismiss by focusing on reconsideration with impact analysis.

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 explicit guidance on when to use this tool versus alternatives is provided. While it implies usage for flagging decisions, it doesn't specify prerequisites, exclusions, or compare to siblings like twining_override or twining_verify, leaving the agent to infer context.

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/daveangulo/twining-mcp'

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