Skip to main content
Glama

twining_override

Override a decision by providing a reason, recording who made the change, and optionally creating a replacement decision automatically.

Instructions

Override a decision with a reason. Sets the decision to overridden status, records who overrode it and why, and optionally creates a replacement decision automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
decision_idYesID of the decision to override
reasonYesReason for the override
new_decisionNoSummary of the replacement decision to auto-create
overridden_byNoWho is overriding (default: "human")

Implementation Reference

  • Registration of the 'twining_override' tool within the server.
    server.registerTool(
      "twining_override",
      {
        description:
          "Override a decision with a reason. Sets the decision to overridden status, records who overrode it and why, and optionally creates a replacement decision automatically.",
        inputSchema: {
          decision_id: z.string().describe("ID of the decision to override"),
          reason: z.string().describe("Reason for the override"),
          new_decision: z
            .string()
            .optional()
            .describe("Summary of the replacement decision to auto-create"),
          overridden_by: z
            .string()
            .optional()
            .describe('Who is overriding (default: "human")'),
        },
      },
      async (args) => {
  • The core logic of the 'twining_override' tool is implemented in the 'override' method of the Decisions engine.
    async override(
      decisionId: string,
      reason: string,
      newDecision?: string,
      overriddenBy?: string,
    ): Promise<{
      overridden: boolean;
      old_summary: string;
      new_decision_id?: string;
    }> {
      const decision = await this.decisionStore.get(decisionId);
      if (!decision) {
        throw new TwiningError(
          `Decision not found: ${decisionId}`,
          "NOT_FOUND",
        );
      }
    
      // Set status to overridden with extra fields
      await this.decisionStore.updateStatus(decisionId, "overridden", {
        overridden_by: overriddenBy ?? "human",
        override_reason: reason,
      });
    
      // Post override entry to blackboard (internal — bypasses decision rejection)
      const overrider = overriddenBy ?? "human";
      await this.blackboardEngine.post({
        entry_type: "decision",
        summary:
          `Override: ${decision.summary} -- overridden by ${overrider}`.slice(
            0,
            200,
          ),
        detail: reason,
        tags: [decision.domain],
        scope: decision.scope,
        agent_id: overrider,
        _internal: true,
      });
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool sets a decision to 'overridden status', records override details, and can auto-create a replacement, which covers key behavioral traits. However, it does not mention permissions, side effects (e.g., impact on related decisions), or error handling, leaving gaps for a mutation tool.

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, well-structured sentence that efficiently conveys the tool's purpose, actions, and optional feature. It is front-loaded with the core action and avoids unnecessary words, making it easy to parse quickly.

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 no annotations and no output schema, the description adequately covers the basic operation but lacks details on permissions, side effects, or return values. For a mutation tool with 4 parameters, it is minimally complete but could benefit from more behavioral context to fully guide an agent.

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 parameters (decision_id, reason, new_decision, overridden_by). The description adds minimal value beyond the schema, such as implying 'new_decision' is optional for auto-creation, but does not provide additional syntax or format details. Baseline 3 is appropriate when schema does the heavy lifting.

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 specific action ('Override a decision with a reason'), the resource ('decision'), and the outcome ('Sets the decision to overridden status, records who overrode it and why, and optionally creates a replacement decision automatically'). It distinguishes itself from siblings like 'twining_decide' (likely for initial decisions) and 'twining_reconsider' (which might review rather than override).

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

Usage Guidelines3/5

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

The description implies usage when overriding a decision is needed, but does not explicitly state when to use this tool versus alternatives like 'twining_reconsider' or 'twining_dismiss'. It mentions optional auto-creation of a replacement decision, which provides some context, but lacks clear exclusions or prerequisites.

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