Skip to main content
Glama
Sign In
agent-memory-sqlite

agent-memory-sqlite

by Urthella
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

recall

Read-only

Search saved memories by keywords to retrieve relevant facts, decisions, and conventions, ranked by BM25 relevance with recency and project scoping.

Instructions

Search saved memories by keywords. Best matches first (BM25), with recent memories ranked higher.

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
limitNo
queryYes
projectNoProject name. Defaults to "app". Use "*" for all projects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

readOnlyHint=true already covers the safety profile, and the description usefully adds ranking behavior (BM25 with a recency boost), which is real behavioral context. It does not state what each result contains (full memory text, score, snippet) or how limit interacts with ranking.

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?

Two short sentences, front-loaded with the action and then the ranking rule; no wasted clauses. It is arguably too terse for the undocumented parameters, but the structure itself is clean.

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?

For a tool with 3 parameters, 33% schema coverage, no output schema, and only a readOnly annotation, the description leaves too much open: query semantics, limit defaults, and result shape are all unstated. A few words on those would make recall vs recent decidable.

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

Parameters2/5

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

Schema coverage is only 33% — only `project` is documented (default "app", "*" for all). The description says nothing about `query` (keyword/BM25 syntax vs natural language) or `limit` (default, max 50) beyond the word 'keywords', so it does not compensate for the gap.

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?

Clear specific verb (search) plus resource (saved memories) and the mechanism (by keywords). It distinguishes itself from `remember`/`forget` by being a retrieval tool, but never explicitly separates it from the sibling `recent`, which likely also returns memories.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no mention of the sibling `recent` as an alternative for time-ordered browsing without keywords. The usage is only implied by the phrase 'by keywords'.

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