Skip to main content
Glama

inspect

View memory decay status, relevance scores, and ages to debug and analyze stored information in AI systems.

Instructions

See all memories with decay status, relevance scores, and ages. Debug view.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The implementation of the inspect tool logic.
    function handleInspect() {
      const memories = loadMemories();
      const now = Date.now();
    
      const inspected = memories.map(m => {
        const rel = computeRelevance(m, now);
        return {
          id: m.id,
          content: m.content.slice(0, 80) + (m.content.length > 80 ? '...' : ''),
          category: m.category,
          mentions: m.mention_count,
          age_days: rel.age_days,
          relevance: rel.relevance,
          decay: rel.decay,
          status: rel.status,
        };
      }).sort((a, b) => b.relevance - a.relevance);
    
      return { memories: inspected, total: inspected.length };
    }
  • index.js:420-423 (registration)
    MCP tool definition for 'inspect'.
      name: 'inspect',
      description: 'See all memories with decay status, relevance scores, and ages. Debug view.',
      inputSchema: { type: 'object', properties: {} }
    },
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 disclosure burden. It successfully indicates what data is returned (decay status, scores, ages), but lacks safety context— it does not explicitly state this is read-only/non-destructive, whether it triggers side effects (e.g., updating last-accessed timestamps), or performance characteristics of scanning 'all' memories.

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?

Two short sentences with zero waste. Critical metadata fields are listed upfront, and 'Debug view' acts as an efficient semantic tag. Every word earns its place.

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?

For a zero-parameter inspection tool without output schema, the description is nearly complete. It compensates for the missing output schema by enumerating the specific fields returned (decay status, relevance, age). Minor gap: could explicitly confirm this returns a list/array of memory objects.

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

Parameters4/5

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

Input schema contains zero parameters, establishing a baseline of 4 per scoring rules. The description correctly implies no filtering is possible ('See all'), which aligns with the empty schema.

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?

Excellent specificity: 'See all memories' establishes the verb and resource, while listing 'decay status, relevance scores, and ages' precisely defines the scope. The 'Debug view' tag effectively distinguishes it from functional siblings like 'recall' (production retrieval) and 'stats' (aggregation).

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 'Debug view' label implies when to use the tool (diagnostic scenarios), but there is no explicit guidance contrasting it with 'recall' (which likely retrieves specific memories) or 'stats' (which likely provides summaries), nor does it state when not to use it.

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/ShipItAndPray/mcp-memory'

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