Skip to main content
Glama

feedback_summary

Read-only

Summarize recent user feedback to identify patterns and insights for improvement.

Instructions

Get summary of recent feedback

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
recentNo

Implementation Reference

  • The function `feedbackSummary` in `scripts/feedback-loop.js` calculates and formats the feedback summary report, including statistics like positive/negative feedback, approval rates, and delegation metrics.
    function feedbackSummary(recentN = 20) {
      const { FEEDBACK_LOG_PATH } = getFeedbackPaths();
      const entries = readJSONL(FEEDBACK_LOG_PATH);
      if (entries.length === 0) {
        return '## Feedback Summary\nNo feedback recorded yet.';
      }
    
      const recent = entries.slice(-recentN);
      const positive = recent.filter((e) => e.signal === 'positive').length;
      const negative = recent.filter((e) => e.signal === 'negative').length;
      const pct = Math.round((positive / recent.length) * 100);
    
      const analysis = analyzeFeedback(FEEDBACK_LOG_PATH);
    
      const lines = [
        `## Feedback Summary (last ${recent.length})`,
        `- Positive: ${positive}`,
        `- Negative: ${negative}`,
        `- Approval: ${pct}%`,
        `- Overall approval: ${Math.round(analysis.approvalRate * 100)}%`,
      ];
    
      if (analysis.delegation) {
        lines.push(`- Delegation attempts: ${analysis.delegation.attemptCount}`);
        lines.push(`- Delegation accepted/rejected/aborted: ${analysis.delegation.acceptedCount}/${analysis.delegation.rejectedCount}/${analysis.delegation.abortedCount}`);
        lines.push(`- Delegation verification failure rate: ${Math.round((analysis.delegation.verificationFailureRate || 0) * 100)}%`);
      }
    
      if (analysis.boostedRisk) {
        lines.push(`- Boosted risk base rate: ${Math.round((analysis.boostedRisk.baseRate || 0) * 100)}%`);
        lines.push(`- Boosted risk mode: ${analysis.boostedRisk.mode}`);
        if (analysis.boostedRisk.highRiskDomains.length > 0) {
          const topDomain = analysis.boostedRisk.highRiskDomains[0];
          lines.push(`- Highest-risk domain: ${topDomain.key} (${Math.round(topDomain.riskRate * 100)}%)`);
        }
      }
  • The `callToolInner` function in `adapters/mcp/server-stdio.js` maps the MCP tool `feedback_summary` to the `feedbackSummary` function, passing the `recent` argument.
    case 'feedback_summary':
      return toTextResult(feedbackSummary(Number(args.recent || 20)));
Behavior3/5

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

The annotations declare readOnlyHint=true, indicating this is a safe read operation. The description adds minimal behavioral context beyond this, as 'Get summary' implies reading data without specifying format, scope, or limitations. It doesn't contradict annotations, but provides little additional behavioral insight.

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 four words, with zero wasted language. It's front-loaded with the core purpose and contains no unnecessary elaboration, making it efficient for quick understanding.

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 the tool has a parameter with no schema documentation, no output schema, and only basic annotations, the description is insufficient. It doesn't explain what the summary contains, how the 'recent' parameter works, or what format the output takes, leaving significant gaps for effective tool use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter ('recent') with 0% description coverage in the schema itself. The tool description provides no information about this parameter—what 'recent' means, what units it uses (e.g., days, number of items), or how it affects the summary. This leaves the parameter poorly documented.

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 'Get summary of recent feedback' clearly states the verb ('Get') and resource ('summary of recent feedback'), making the purpose understandable. However, it's somewhat vague about what constitutes a 'summary' and doesn't differentiate from sibling tools like 'feedback_stats' or 'capture_feedback', which appear related to feedback processing.

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. With sibling tools like 'feedback_stats' and 'capture_feedback' available, there's no indication of what makes this tool distinct or when it should be preferred over other feedback-related tools.

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/IgorGanapolsky/mcp-memory-gateway'

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