Skip to main content
Glama

recall

Idempotent

Search memories by semantic similarity, refine low-confidence results, or provide feedback to improve future retrieval.

Instructions

Search memories by semantic similarity, refine low-confidence results, or give feedback.

MODES:

  • Search (default): recall("project architecture decisions")

  • Refine: recall("PostgreSQL vs MySQL decision", refine_from="database choice", refine_exclude=["rid1"])

  • Feedback: recall(query="", feedback_rid="abc", feedback="relevant")

WHEN TO USE:

  • At conversation start: recall a summary of the user's first message.

  • When user references past decisions, people, preferences, or "last time".

  • When unsure about something the user assumes you know.

  • Use refine_from when first recall had low confidence (< 0.5).

  • Use feedback_rid after using a recalled memory to improve future retrieval.

QUERY GUIDELINES:

  • Use a short natural language sentence (5-10 words), NOT keyword lists.

  • GOOD: "private retail demo with shift brain"

  • GOOD: "user's architecture preferences"

  • BAD: "private retail demo stunning pitch shift brain yantrikdb rewritten reality private operations memory"

  • Keyword stuffing degrades recall quality and is slower. Ask one focused question per call.

  • If you need multiple topics, make separate recall calls.

Args: query: Short natural language sentence (5-10 words). NOT a keyword list. top_k: Max results (default 10). 3-5 for focused, 10-20 for broad. memory_type: Filter: "semantic", "episodic", "procedural". domain: Filter: "work", "preference", "architecture", "people", etc. source: Filter: "user", "inference", "document", "system". namespace: Filter by namespace. include_consolidated: Include merged memories. expand_entities: Use knowledge graph boosting (default True). refine_from: Original query text to refine from. query becomes the refinement. refine_exclude: Memory IDs to exclude when refining. feedback_rid: Memory ID to give feedback on (switches to feedback mode). feedback: "relevant" or "irrelevant" (required with feedback_rid). feedback_score: Score at retrieval (helps learning). feedback_rank: Rank position at retrieval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
top_kNo
domainNo
sourceNo
feedbackNo
namespaceNo
memory_typeNo
refine_fromNo
feedback_ridNo
feedback_rankNo
feedback_scoreNo
refine_excludeNo
expand_entitiesNo
include_consolidatedNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Discloses behavioral traits beyond annotations: modes with detailed behavior, query guidelines (short natural language, no keyword stuffing), refine/feedback mechanics, and confidence thresholds. Annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) are consistent, and description adds crucial context about how the tool behaves in different modes.

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?

Description is relatively long but well-structured with clear sections (MODES, WHEN TO USE, QUERY GUIDELINES, Args). Each section is front-loaded with key information. While every sentence adds value, some redundancy exists (e.g., query guidelines repeated in args). Still efficient for the complexity.

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 14 parameters, 0% schema coverage, and an output schema exists, the description covers all necessary aspects: all parameters, mode behaviors, query guidelines, and use cases. It compensates fully for missing schema descriptions and provides complete guidance for an agent to invoke and select the tool correctly.

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 coverage is 0% (no descriptions in schema), so description carries full burden. It provides detailed meaning for all 14 parameters: query format examples, top_k usage ranges, filter purposes (memory_type, domain, source, namespace), and special parameters like refine_from, refine_exclude, feedback_rid with usage explanation. This significantly adds value beyond the 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?

Description clearly states the tool searches memories by semantic similarity with three distinct modes: Search, Refine, Feedback. The verb 'search', 'refine', and 'feedback' along with 'memories' as resource makes purpose explicit. Among siblings like 'remember', 'forget', 'memory', the description differentiates by listing modes and specific use cases.

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?

Provides explicit when-to-use scenarios ('At conversation start', 'When user references past decisions') and specific guidelines for refine mode and feedback mode. However, it does not explicitly state when not to use this tool or provide direct alternatives from siblings, just implies context.

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/yantrikos/yantrikdb-mcp'

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