Skip to main content
Glama
autoexecbatman

Enhanced Architecture MCP

reasoning_assist

Provides structured reasoning assistance to break down complex problems into logical steps using specified models.

Instructions

Structured reasoning assistance for complex problems

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
problemYesProblem statement requiring reasoning
stepsNoNumber of reasoning steps requested
modelNoModel to use for reasoningarchitecture-reasoning:latest

Implementation Reference

  • The main handler function for 'reasoning_assist' that constructs a structured multi-step reasoning prompt based on the problem and number of steps, then delegates to the local AI via queryLocalAI.
      async reasoningAssist(problem, steps = 5, model = 'architecture-reasoning:latest') {
        const structuredPrompt = `Problem: ${problem}
    
    Please provide a structured reasoning approach with exactly ${steps} steps:
    
    1. [Step 1 reasoning]
    2. [Step 2 reasoning]
    3. [Step 3 reasoning]
    ${steps > 3 ? '4. [Step 4 reasoning]' : ''}
    ${steps > 4 ? '5. [Step 5 reasoning]' : ''}
    ${steps > 5 ? Array.from({length: steps - 5}, (_, i) => `${i + 6}. [Step ${i + 6} reasoning]`).join('\n') : ''}
    
    Conclusion: [Final reasoning conclusion]
    
    Think step by step and show your reasoning process clearly.`;
    
        return await this.queryLocalAI(structuredPrompt, model, 0.6);
      }
  • Input schema definition for the reasoning_assist tool, specifying required 'problem' string, optional 'steps' number (default 5), and 'model' string (default 'architecture-reasoning:latest').
    inputSchema: {
      type: 'object',
      properties: {
        problem: {
          type: 'string',
          description: 'Problem statement requiring reasoning'
        },
        steps: {
          type: 'number',
          description: 'Number of reasoning steps requested',
          default: 5
        },
        model: {
          type: 'string',
          description: 'Model to use for reasoning',
          default: 'architecture-reasoning:latest'
        }
      },
      required: ['problem']
    }
  • Tool registration in the ListTools response, defining name, description, and input schema.
    {
      name: 'reasoning_assist',
      description: 'Structured reasoning assistance for complex problems',
      inputSchema: {
        type: 'object',
        properties: {
          problem: {
            type: 'string',
            description: 'Problem statement requiring reasoning'
          },
          steps: {
            type: 'number',
            description: 'Number of reasoning steps requested',
            default: 5
          },
          model: {
            type: 'string',
            description: 'Model to use for reasoning',
            default: 'architecture-reasoning:latest'
          }
        },
        required: ['problem']
      }
    },
  • Registration of the tool handler in the CallToolRequest switch statement, routing calls to the reasoningAssist method.
    case 'reasoning_assist':
      return await this.reasoningAssist(args.problem, args.steps, args.model);
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'structured reasoning assistance' but doesn't explain what that means operationally: what format the output takes, whether it's deterministic, what happens with different step counts, or any limitations. For a reasoning tool with zero annotation coverage, this leaves significant behavioral gaps.

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 extremely concise at just 5 words. Every word earns its place by conveying the core function. There's no wasted language or unnecessary elaboration. The structure is front-loaded with the essential information.

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

Completeness2/5

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

Given this is a reasoning tool with 3 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what kind of output to expect, how the reasoning is structured, or what makes it different from sibling tools. For a tool that presumably produces complex reasoning outputs, more context is needed.

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 fully documents all three parameters (problem, steps, model). The description adds no additional meaning about parameters beyond what's in the schema. It doesn't explain how 'steps' affects reasoning quality, what models are available, or provide examples of appropriate 'problem' statements. Baseline 3 is appropriate when schema does all the work.

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

Purpose3/5

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

The description 'Structured reasoning assistance for complex problems' states a general purpose but lacks specificity about what the tool actually does. It mentions 'reasoning assistance' but doesn't specify the verb (generate? analyze? evaluate?) or the resource (what kind of reasoning output?). It distinguishes from siblings only by being about 'reasoning' rather than analysis or querying, but remains vague about the actual operation.

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 use this tool versus alternatives like 'hybrid_analysis', 'model_list', 'query_local_ai', or 'token_efficient_reasoning'. There's no mention of appropriate contexts, prerequisites, or exclusions. The agent must infer usage from the tool name and vague description alone.

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/autoexecbatman/arch-mcp'

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