Skip to main content
Glama

reject_instinct

Deactivate an instinct and reduce its confidence by providing its ID, helping manage automated context rules in persistent chat sessions.

Instructions

Reject/deactivate an instinct and lower its confidence

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesInstinct ID to reject

Implementation Reference

  • The core implementation of the 'reject' logic, which deactivates an instinct and adjusts its confidence.
    /** Reject an instinct: deactivate and drop confidence. */
    async reject(id: string): Promise<Instinct> {
      const entry = await this.find(id);
      if (!entry) throw new Error(`Instinct not found: ${id}`);
    
      const { file, instinctFile, instinct } = entry;
      instinct.active = false;
      instinct.confidence = Math.max(0, instinct.confidence - 0.3);
      // Ensure min_confidence doesn't exceed new confidence (Zod invariant)
      instinct.min_confidence = Math.min(instinct.min_confidence, instinct.confidence);
      instinct.updated_at = new Date().toISOString();
    
      // Record rejection in outcome_log
      const outcome: OutcomeEntry = {
        timestamp: new Date().toISOString(),
        result: 'negative',
        delta_confidence: -0.3,
        note: 'Rejected via CLI',
      };
      instinct.outcome_log.push(outcome);
    
      instinctFile.instincts[id] = instinct;
      await this.loader.save(file, instinctFile);
    
      return instinct;
    }
  • The MCP tool handler in the server that invokes the registry's reject method.
    case 'reject_instinct': {
      const id = String(args?.['id'] ?? '');
      if (!id) return { content: [{ type: 'text', text: 'Error: id is required' }] };
      try {
        const instinct = await registry.reject(id);
        return { content: [{ type: 'text', text: JSON.stringify({ rejected: id, confidence: instinct.confidence, active: instinct.active }, null, 2) }] };
      } catch (e) {
        return { content: [{ type: 'text', text: `Error: ${e instanceof Error ? e.message : String(e)}` }] };
      }
    }
  • Registration of the 'reject_instinct' tool in the MCP server list.
      name: 'reject_instinct',
      description: 'Reject/deactivate an instinct and lower its confidence',
      inputSchema: {
        type: 'object' as const,
        properties: {
          id: { type: 'string', description: 'Instinct ID to reject' },
        },
        required: ['id'],
      },
    },
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses the side effect of lowering confidence and implies state change via 'deactivate', but omits critical mutation details like reversibility, persistence, or whether this operation is destructive.

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, efficient sentence with no filler. Every word contributes to understanding the operation (dual verbs 'Reject/deactivate', target 'instinct', and effect 'lower its confidence').

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 tool's simplicity (single parameter, no output schema, no nested objects), the description adequately covers the core action but leaves gaps regarding return values, error conditions, or the relationship between rejection and the confidence metric.

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% (the 'id' parameter is fully described in the schema), establishing a baseline of 3. The description does not add parameter-specific details like ID format or lookup requirements beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the action ('Reject/deactivate') and resource ('instinct'), and distinguishes itself from siblings like 'approve_instinct' and 'store_instinct' through opposing verbs. However, it lacks domain context explaining what an 'instinct' represents in this system.

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?

The description provides no guidance on when to reject versus approve an instinct, nor does it mention prerequisites or conditions for use. The agent must infer usage context solely from the tool name and sibling names.

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/doobidoo/MCP-Context-Provider'

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