Skip to main content
Glama

soul_framework

Retrieve a behavioral framework with complete details: description, evidence history, tier, and relationships. Input the framework name or ID to access its full record.

Instructions

Load a single framework with full details: description, evidence history, tier, and relationships.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesFramework name (case-insensitive, partial match) or ID

Implementation Reference

  • Main handler function for the soul_framework tool. Initializes the FrameworkEngine, searches for a framework by exact name/ID or partial match, and returns full framework details via renderFullFramework().
    export async function handleSoulFramework(name: string): Promise<string> {
      const engine = new FrameworkEngine();
      const store = await engine.initialize();
    
      // Search by name (case-insensitive) or by ID
      const fw = store.frameworks.find(
        (f) =>
          f.name.toLowerCase() === name.toLowerCase() ||
          f.id === name,
      );
    
      if (!fw) {
        // Try partial match
        const partial = store.frameworks.find(
          (f) => f.name.toLowerCase().includes(name.toLowerCase()),
        );
        if (partial) {
          return renderFullFramework(partial);
        }
    
        const available = store.frameworks
          .filter((f) => f.status !== "retired")
          .map((f) => `- ${f.name} (${f.id})`)
          .join("\n");
        return `Framework "${name}" not found. Available:\n${available}`;
      }
    
      return renderFullFramework(fw);
    }
  • Renders a full framework detail view including description, evidence history, related frameworks, contradictions, and supersedes relationships.
    function renderFullFramework(fw: Framework): string {
      const confirmed = fw.evidence.filter((e) => e.type === "confirmed");
      const contradicted = fw.evidence.filter((e) => e.type === "contradicted");
    
      const lines: string[] = [];
      lines.push(`# ${fw.name}`);
      lines.push("");
      const tier = fw.evidenceTier ?? "hypothesis";
      lines.push(`**Status**: ${fw.status} | **Tier**: ${tier} | **Source**: ${fw.source}`);
      lines.push(`**Domain**: ${fw.domain} | **Applied**: ${fw.applicationCount} times | **Last tested**: ${formatDate(fw.lastTestedAt)}`);
      lines.push("");
      lines.push("## Description");
      lines.push("");
      lines.push(fw.description);
    
      // Evidence history
      lines.push("");
      lines.push(`## Evidence (${confirmed.length} confirmed, ${contradicted.length} contradicted)`);
      if (fw.evidence.length === 0) {
        lines.push("*(no evidence yet)*");
      } else {
        for (const e of fw.evidence) {
          lines.push(`- [${formatDate(e.timestamp)}] **${e.type}**: ${e.context}`);
        }
      }
    
      // Related frameworks
      if (fw.relatedFrameworks.length > 0) {
        lines.push("");
        lines.push(`## Related: ${fw.relatedFrameworks.join(", ")}`);
      }
      if (fw.contradicts.length > 0) {
        lines.push(`## Contradicts: ${fw.contradicts.join(", ")}`);
      }
      if (fw.supersedes.length > 0) {
        lines.push(`## Supersedes: ${fw.supersedes.join(", ")}`);
      }
    
      return lines.join("\n");
    }
  • Utility function to format a timestamp as an ISO date string (YYYY-MM-DD).
    function formatDate(timestamp: number): string {
      return new Date(timestamp).toISOString().slice(0, 10);
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden. It only states 'Load' (implying read-only) and lists return fields, but does not disclose potential errors, authentication needs, or side effects. The lack of behavioral context beyond 'load' is insufficient.

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, concise sentence that front-loads the action and resource, then lists key details. Every word is essential, with no redundancy or filler.

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?

Given the simple input (one param with good schema) and no output schema, the description adequately explains the return fields (description, evidence history, tier, relationships). It is nearly complete, though it could mention that it returns a single framework (implied by 'a single framework').

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% with a clear parameter description: 'Framework name (case-insensitive, partial match) or ID'. The tool description adds no additional semantic meaning beyond what the schema already provides, meeting the baseline expectation.

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 verb 'Load' and the resource 'a single framework with full details', listing specific attributes (description, evidence history, tier, relationships). This distinguishes it from sibling tools like soul_activate, soul_context, etc., which have different actions.

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 such as soul_read or soul_context. There is no mention of prerequisites, context, or exclusions, leaving the agent to infer usage from the tool name and siblings.

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/DomDemetz/claude-soul'

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