Skip to main content
Glama
Filipe-Soares-de-Almeida

MemAI

by Filipe-Soares-de-Almeida
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

recall

Retrieve long-term notes saved with note() using BM25 relevance search, scoped to type='note' for timeless facts, rules, and decisions.

Instructions

Recall long-term knowledge saved with note() (type='note').

The dedicated verb for "bring back what I noted": a BM25 search scoped to type='note', ranked by relevance -- which is what you want for timeless facts/rules/decisions. note() has no recency warm-up hook the way checkpoints have pulse(); this (or search(type='note')) is how notes come back.

Returns {"results": [...], "est_tokens": N}. Content is snippet-truncated -- call get_memory(uid) for the full record; a result's est_tokens estimates what that full record costs, and the top-level est_tokens is the sum over the results.

domain scopes to a path and everything nested under it, and resolves a bare deep segment the same way search() does. Results carry the same succeeded_by / collapsed annotations search() explains.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
domainNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / limit / default
      Previous value: -20New value: +10
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "items": {
-        "additionalProperties": true,
-        "type": "object"
-      },
-      "title": "Result",
-      "type": "array"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "recallOutput",
-  "type": "object"
-}New value: +null
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses snippet truncation, the est_tokens cost semantics (per-result and top-level sum), domain scoping/resolution behavior, and the succeeded_by/collapsed annotations carried by results. It stops short of stating permission/auth requirements, but for a read tool this is a strong disclosure.

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?

Front-loaded with the core verb and scope, then layered detail. Multi-sentence and somewhat dense, but each sentence (alternatives, return shape, truncation, domain) earns its place rather than padding.

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

Completeness4/5

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

No output schema exists, and the description fills that gap by describing the return shape and token-cost fields; it also covers truncation and the domain parameter. The undocumented limit parameter is the main remaining gap, keeping it from a 5.

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 coverage is 0%, so the description must compensate. It gives useful semantics for domain (path scoping, bare-segment resolution) but says nothing about limit (default 10) or query beyond the implied search. Partial compensation for a 0%-coverage 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?

States a specific verb ('recall') plus resource and scope ('long-term knowledge saved with note()', 'BM25 search scoped to type='note''), and cleanly distinguishes itself from siblings search() and get_memory(). An agent can tell exactly what this does without opening any schema.

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

Usage Guidelines5/5

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

Explicitly names when to use it ('timeless facts/rules/decisions'), names the alternative ('search(type='note')') that also works, and names the follow-up tool ('call get_memory(uid) for the full record'). Nothing is left to inference.

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