Skip to main content
Glama

Metis · Memory Curator — Recall

recall

Search all Metis memory layers in one query—notes, agent findings, project decisions, PDF knowledge, ideas, and session history—to get ranked results with source attribution.

Instructions

Search across ALL memory layers in one call.

The unified front door to everything Metis remembers — personal notes,
agent findings, project decisions, PDF knowledge, ideas, and session
history. Returns ranked results with source attribution.

Searches up to 6 layers and merges results using Reciprocal Rank Fusion:
  1. Memory palace (memory_entries — keyword)
  2. Episodic memory (events — vector + keyword)
  3. Semantic memory (concepts — vector + keyword)
  4. Procedural memory (workflows — vector + keyword)
  5. Knowledge databases (PDF chunks — vector)
  6. Ideas (ideas table — keyword)

Use scope/agent_id/project_id to narrow results:
  recall("malaria diagnostics")                      → everything
  recall("search patterns", agent_id="librarian")    → librarian's wisdom
  recall("elimination", project_id="article-1")      → Article 1 decisions
  recall("mixed models", scope="global")             → cross-cutting knowledge

Args:
    query: Natural language search query.
    scope: Filter by scope: 'global', 'agent', 'project', 'session'.
        Empty string (default) searches all scopes.
    agent_id: Filter to memories from a specific agent (e.g. 'librarian').
    project_id: Filter to memories linked to a specific project.
    layers: Comma-separated layers to search. Options: 'memory', 'episodic',
        'semantic', 'procedural', 'knowledge', 'ideas', or 'all' (default).
    top_k: Number of results to return (default 10).
    recency_half_life: Days until recency boost halves (default 90). Set to 0
        to disable recency weighting. A 90-day-old entry gets ~37% of a
        fresh entry's time bonus; 180-day ~14%.

Returns:
    Ranked results from across all matching layers, each with its source
    layer, relevance score, timestamp, and content preview.

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
queryYes
scopeNo
top_kNo
layersNoall
agent_idNo
project_idNo
recency_half_lifeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.4

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it discloses the RRF merge strategy, the six underlying sources, result ranking with source attribution, and precise recency-decay behavior (37% at 90 days, 14% at 180). It never explicitly states read-only/no-side-effects or any auth/rate-limit constraints, which is the remaining gap for an annotation-free tool.

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 purpose, then cleanly sectioned into layers, usage examples, args, and returns. Slightly redundant in that the six-layer list and the `layers` parameter enumeration overlap, but the list adds table-level provenance that the arg docs don't, so little is truly wasted.

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?

For a 7-parameter federated search with no annotations and a rich underlying system, the description covers scope, layer selection, ranking algorithm, recency tuning, and filter semantics. An output schema exists, and the description still sketches return shape, so nothing an agent needs to call it correctly is missing.

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%, and the description fully compensates: it documents all seven parameters including defaults, the enumerated scope values ('global','agent','project','session'), the layer token list, top_k, and a quantitative explanation of recency_half_life including how to disable it. This adds meaning well beyond the bare schema titles.

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 and resource ('Search across ALL memory layers in one call') and frames itself as 'the unified front door to everything Metis remembers', enumerating the six layers it covers. An agent can distinguish this broad federated recall from narrower siblings like search_memory or semantic_search 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 Guidelines4/5

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

Provides four concrete invocation examples showing how scope/agent_id/project_id narrow the search, which gives clear guidance on when to use which filter combination. It never names an alternative tool or states when NOT to use this one (e.g., versus search_memory, search_session_memory, or semantic_search), leaving that inference to the agent.

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