shared-memory

memory_search

Query the shared memory to recall notes, preferences, and decisions across Claude windows, so conversations start with existing context instead of repeating background.

Instructions

Search the shared memory. Space-separated keywords; matches any by default (match="all" requires every keyword). Empty query returns the most recent entries. Call once at the start of a new conversation.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "memory_search"
  }
}

Input Schema

Name	Required	Description
`tag`	No	Only entries with this exact tag
`limit`	No	Max entries to return (default 50, newest kept)
`match`	No	"any" (default) or "all"
`query`	No	Keywords, may be empty

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 21, 2026

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description carries the full load. It discloses matching semantics (any vs all) and the empty-query recency behavior, which is genuinely useful, but says nothing about ordering, result shape, permissions, or cost/rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action, then matching semantics, then the trigger condition. Every sentence adds information an agent needs.

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?

For a small read-oriented search tool with fully documented parameters, this is nearly complete. The only gap is that with no output schema, the agent gets no hint of what an entry contains or how results are ordered beyond 'newest kept'.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it explains that space-separated keywords are OR'd by default and that an empty query returns recent entries — behavior the 'query' schema entry does not state.

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 the shared memory') and clearly contrasts with memory_save and memory_delete by implication. It's clear what the tool does, though it never explicitly names how it differs from its siblings.

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 a concrete invocation rule: 'Call once at the start of a new conversation', plus the fallback behavior for an empty query. It lacks explicit exclusion guidance (e.g., when to prefer listing tags or repeated searches), but the timing cue is strong.

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

Deploy Server