Skip to main content
Glama

recall_memory

Retrieve stored information from memory using specific keys and categories to access previously saved data.

Instructions

recall|remember|what was|remind|retrieve - Retrieve from memory

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesMemory key to retrieve
categoryNoMemory category to search in

Implementation Reference

  • The main handler function that executes the recall_memory tool logic. It retrieves a memory entry by key using the MemoryManager singleton and returns the memory content or an error message.
    export async function recallMemory(args: { key: string; category?: string }): Promise<ToolResult> {
      const { key: recallKey } = args;
    
      try {
        const memoryManager = MemoryManager.getInstance();
        const memory = memoryManager.recall(recallKey);
    
        if (memory) {
          return {
            content: [{ type: 'text', text: `${memory.key}: ${memory.value}\n[${memory.category}]` }]
          };
        } else {
          return {
            content: [{ type: 'text', text: `✗ Not found: "${recallKey}"` }]
          };
        }
      } catch (error) {
        return {
          content: [{ type: 'text', text: `✗ Error: ${error instanceof Error ? error.message : 'Unknown error'}` }]
        };
      }
    }
  • The ToolDefinition object defining the schema, name, description, and input parameters for the recall_memory tool.
    export const recallMemoryDefinition: ToolDefinition = {
      name: 'recall_memory',
      description: 'recall|remember|what was|remind|retrieve - Retrieve from memory',
      inputSchema: {
        type: 'object',
        properties: {
          key: { type: 'string', description: 'Memory key to retrieve' },
          category: { type: 'string', description: 'Memory category to search in' }
        },
        required: ['key']
      },
      annotations: {
        title: 'Recall Memory',
        audience: ['user', 'assistant']
      }
    };
  • src/index.ts:638-639 (registration)
    Registration in the tool execution switch statement in index.ts, dispatching calls to the recallMemory handler.
    case 'recall_memory':
      return await recallMemory(args as any) as CallToolResult;
  • src/index.ts:126-126 (registration)
    Inclusion of recallMemoryDefinition in the tools array for tool listing and discovery.
    recallMemoryDefinition,
  • src/index.ts:63-63 (registration)
    Import of the recallMemory handler and definition from its module.
    import { recallMemory, recallMemoryDefinition } from './tools/memory/recallMemory.js';
Behavior2/5

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

Annotations only provide a title ('Recall Memory'), which adds no behavioral hints. The description doesn't disclose any behavioral traits: it doesn't state if this is a read-only operation (implied by 'retrieve' but not explicit), what happens if the key doesn't exist (e.g., returns null or error), or any rate limits or authentication needs. For a tool with minimal annotations, the description carries full burden and fails to provide necessary context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise but poorly structured. It's a single phrase with pipe-separated synonyms, which is inefficient and lacks front-loading of key information. While it avoids verbosity, the structure doesn't effectively communicate purpose or usage, making it less helpful than a more organized sentence would be.

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 no output schema and minimal annotations, the description is incomplete. It doesn't explain what is returned (e.g., memory content, metadata, or error handling), nor does it cover behavioral aspects like idempotency or side effects. For a retrieval tool with siblings, more context is needed to guide the agent effectively.

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%, with clear descriptions for 'key' and 'category' parameters. The description adds no meaning beyond the schema—it doesn't explain what a 'memory key' represents, how categories are used, or provide examples. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but the description doesn't compensate or enhance understanding.

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

Purpose2/5

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

The description 'recall|remember|what was|remind|retrieve - Retrieve from memory' is tautological, essentially restating the tool name 'recall_memory' with synonyms. It doesn't specify what resource is being retrieved (e.g., stored data, context, or specific memory entries) or distinguish it from sibling tools like 'list_memories', 'search_memories', or 'retrieve_memory' (though the last isn't listed). The pipe-separated synonyms add no clarity about the actual function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

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. It doesn't mention sibling tools like 'list_memories' (for listing all memories) or 'search_memories' (for broader searches), nor does it specify prerequisites, such as needing a saved memory first. There's no context on appropriate use cases or exclusions.

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/ssdeanx/ssd-ai'

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