Skip to main content
Glama

recall_memories

Read-onlyIdempotent

Search and retrieve saved memories using semantic ranking and optional filters for precise results. Find relevant information from past conversations quickly.

Instructions

Search and retrieve saved memories with intelligent semantic ranking.

🎯 BASIC SEARCH: recall_memories(query="authentication") → Returns all memories about authentication, ranked by semantic relevance

🔍 FILTERED SEARCH (Phase 2 Knowledge Graph Intelligence): Use filters when you need PRECISION over semantic similarity:

✓ entity="name" - Find memories mentioning specific people/projects/technologies Example: entity="purmemo" → Only memories discussing purmemo

✓ has_observations=true - Find substantial, fact-dense conversations Example: has_observations=true → Only high-quality technical discussions

✓ initiative="project" - Scope to specific initiatives/goals Example: initiative="Q1 OKRs" → Only Q1-related memories

✓ intent="type" - Filter by conversation purpose Options: decision, learning, question, blocker Example: intent="blocker" → Only conversations about blockers

💡 WHEN TO FILTER:

  • Use entity when user asks about specific person/project by name

  • Use has_observations for "detailed" or "substantial" requests

  • Use initiative/stakeholder for project-specific searches

  • Use intent when user asks for decisions, learnings, or blockers

📝 COMBINED EXAMPLES: recall_memories(query="auth", entity="purmemo", has_observations=true) → Find detailed technical discussions about purmemo authentication

recall_memories(query="blockers", intent="blocker", stakeholder="Engineering") → Find engineering team blockers

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query - can be keywords, topics, or specific content
includeChunkedNoInclude chunked/multi-part conversations in results
limitNoMaximum number of memories to return
entityNoFilter by entity name (people, projects, technologies). Use when user asks about a specific person, project, or technology by name. Example: entity="Alice" finds only memories mentioning Alice. More precise than semantic search. Supports partial matching.
initiativeNoFilter by initiative/project name from conversation context. Use when user scopes search to specific project or goal. Example: initiative="Q1 OKRs" finds only Q1-related memories. Supports partial matching (ILIKE).
stakeholderNoFilter by stakeholder (person or team) from conversation context. Use when user asks about specific person's or team's involvement. Example: stakeholder="Engineering Team" finds memories where Engineering Team was mentioned as stakeholder. Supports partial matching (ILIKE).
deadlineNoFilter by deadline date from conversation context (YYYY-MM-DD format). Use when user asks about time-sensitive memories or specific deadlines. Example: deadline="2025-03-31" finds memories with March 31, 2025 deadline. Exact match only.
intentNoFilter by conversation intent/purpose. Options: "decision" (decisions made), "learning" (knowledge gained), "question" (open questions), "blocker" (obstacles/issues). Use when user asks specifically for one of these types. Example: intent="decision" finds only conversations where decisions were made. Exact match only.
has_observationsNoFilter by conversation quality based on extracted observations (atomic facts). Set to true to find substantial, structured conversations with extracted knowledge (high-quality technical discussions, detailed planning). Set to false for lightweight chats. Omit to return all memories regardless of observation count. Use when user asks for "detailed", "substantial", or "in-depth" information.
Behavior5/5

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds valuable context such as 'intelligent semantic ranking,' detailed filtering behavior, and examples of combined searches. This goes beyond annotations by explaining how results are ordered and how queries are processed.

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

Conciseness4/5

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

The description is well-structured with clear sections, emoji headers, and examples. It is front-loaded with a basic search example. However, it is somewhat verbose due to extensive examples and repetition, which could be streamlined without losing clarity.

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

Completeness5/5

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

Given 9 parameters, no output schema, and moderate complexity, the description covers all parameters with detailed explanations, combined examples, and usage guidance. It provides sufficient context for an agent to correctly invoke the tool, though return format is not specified (acceptable without output schema).

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

Parameters5/5

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

Schema description coverage is 100%, with each parameter well-described. The description adds practical examples, usage patterns, and partial matching details for entity, initiative, and stakeholder. This enriches the schema by demonstrating real-world application and clarifying nuanced behaviors like 'ILIKE' matching.

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 'Search and retrieve saved memories with intelligent semantic ranking.' It specifies the verb (search/retrieve), resource (saved memories), and the method (semantic ranking). This distinguishes it from siblings like recall_public (public memories) and get_memory_details (specific details).

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

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a 'WHEN TO FILTER' section that provides explicit context for using each filter parameter, guiding the agent on precision vs. semantic similarity. However, it does not directly compare this tool to sibling tools like recall_public or discover_related_conversations, leaving some ambiguity in tool selection.

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/purmemo-ai/purmemo-mcp'

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