Gnosis Memory

memory_search

Read-only

Search memories by relevance. Up to 32 results.

Query = ALL nouns from the user's message, not just the main one (ranking is automatic). "How does the app cache API calls?" -> "app cache api calls" complete=false results are truncated -> memory_retrieve(id) for full content. Auto-includes all your 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_search"
  }
}

Input Schema

Name	Required	Description
`query`	Yes	Search query -- all relevant nouns.
`expand`	No	Full content for all results (~16K tokens/page). Dedicated research 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

A3.9/5.0

Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false; the description adds real behavioral context on top: a 32-result ceiling, the complete=false truncation flag semantics, and automatic fan-out across all shared collections. It does not explain how ranking works or whether the 32 cap is per-collection or global.

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 purpose and result cap, then layered guidance in short lines with a concrete example. Dense but every line is operational; the parenthetical "ranking is automatic" is the only near-filler.

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 carries the burden and does report the result count ceiling and the complete flag — enough for an agent to call it and know when to follow up. Missing detail on pagination past 32 results and the fields returned keeps it short of complete.

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% and each parameter is documented in detail, so the baseline is 3. The description's query guidance largely restates the schema's "all relevant nouns" wording and says nothing about expand or type_filter, adding little beyond structured fields.

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 relevance") plus a concrete result cap of 32. It distinguishes itself from memory_retrieve by routing truncated results there, but never contrasts itself with the close sibling memory_deep_search, leaving one ambiguity.

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?

Gives actionable query-construction guidance ("ALL nouns from the user's message") and a clear follow-up rule for truncated results via memory_retrieve(id). It does not say when an agent should prefer memory_deep_search or memory_search, so the alternative-selection guidance is incomplete.

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?