Gnosis Memory

memory_deep_search

Read-only

Broad search for a FULL sweep -- every hit on a topic (e.g. before memory_consolidate), not a conversational lookup (that is memory_search). Up to 128 results; requires 2+ keywords ("python" alone = too broad).

Scores: 30+ excellent, 20+ good, <20 weak. Full sweep of a topic intersection. complete=false -> memory_retrieve(id). Read 20+ memories on one topic? -> memory_consolidate a summary future sessions see first. Auto-includes shared collections (fan-out).

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": "memory_deep_search"
  }
}

Input Schema

Name	Required	Description
`query`	Yes	Search query -- 2+ keywords.
`expand`	No	Full content for all results (50K+ tokens). Dedicated large-context agents only.
`type_filter`	No	Filter by type: fact/preference/decision/path/task/task_done/summary/result. Omit=all.
`collection_filter`	No	Limit to one collection name, or "personal". Omit=all. A slug this namespace holds no grant on (even one the account can list elsewhere) returns 0 rows plus a no_grant explanation, never silence.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already supply the safety profile (readOnlyHint=true, openWorldHint=false) and the title carries the 128-result cap, but the description adds genuinely non-obvious behavior: fan-out into shared collections, the score bands used to judge result quality, and the meaning of the complete flag. It does not describe what a single hit contains or whether results are ordered.

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?

The routing distinction is front-loaded and every line carries operational information, with no filler. The telegraphic fragment style ("Scores: 30+ excellent...", "complete=false -> memory_retrieve(id)") is compact but slightly cryptic to parse on first read.

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?

With no output schema, the description still conveys the result shape an agent needs: a capped hit list, a per-hit score with interpretation bands, and a completeness flag. It stops short of describing hit fields or ordering, which leaves a small gap for a search tool whose output is the whole point.

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 100%, so query, expand, type_filter, and collection_filter are already well documented. The description's "2+ keywords" rule duplicates the schema text rather than extending it, and it says nothing about expand or the type/collection filters. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

"Broad search for a FULL sweep -- every hit on a topic" names the verb, the resource, and the scope, then explicitly contrasts with "a conversational lookup (that is memory_search)". An agent can route between the two siblings without opening either 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?

It states when to use (before memory_consolidate, full topic sweep), when not to (conversational lookup -> memory_search), a precondition (2+ keywords, with a concrete counter-example), and follow-up routes for both the empty and heavy-result cases (complete=false -> memory_retrieve, 20+ memories -> memory_consolidate).

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

All Gnosis Memory tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?