Skip to main content
Glama
furui

furui

Recall

recall

Search long-term agent memories by keyword or natural-language query, rank results by relevance and current score, and reinforce every returned memory by resetting its decay clock.

Instructions

Search memories by keyword overlap, ranked by relevance x current score.

Every returned memory is reinforced: its recall_count goes up and its decay clock resets. An empty query returns the strongest memories overall.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of memories to return (1-100).
queryYesNatural-language or keyword query.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full behavioral burden and does so: it discloses that retrieval is a mutating operation, since every returned memory has recall_count incremented and its decay clock reset. That is exactly the non-obvious side effect an agent must know before calling a 'search' tool repeatedly.

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?

Three short sentences, front-loaded with purpose and ranking, then the side effect, then the empty-query edge case. Every sentence carries information not available in the schema or annotations.

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?

An output schema exists, so return-value structure need not be explained, and the two-parameter surface is fully documented in the schema. The remaining complexity that matters for a search tool — ranking basis and the reinforcement side effect — is covered, leaving no gap an agent needs to close before calling it.

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?

Schema coverage is 100%, so both parameters are already documented and the baseline is 3. The description adds meaning the schema does not: the special semantics of an empty query string, which is a valid and useful input mode rather than an error.

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

Purpose4/5

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

States a specific verb and resource ('Search memories by keyword overlap') plus the ranking rule ('relevance x current score'), which is enough for an agent to know this is the retrieval path rather than the write path used by 'remember'. It never names a sibling or explicitly contrasts itself with 'forget'/'prune', so it stops short of full differentiation.

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?

Clear usage context: query for keyword/natural-language lookup, and 'An empty query returns the strongest memories overall' tells the agent how to deliberately retrieve top memories. There is no explicit when-not guidance or named alternative, so it is short of the top band.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools