Skip to main content
Glama
Sign In
agent-memory-router

agent-memory-router

by lss486558354-ship-it
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

search_memory

Search memory index summaries by keyword, type, or recency to find record IDs, then retrieve full content via read_raw_data.

Instructions

在记忆索引中检索，返回摘要列表（不含原文）。

这是访问历史记忆的第一步。不要跳过它直接猜。

Args: keyword: 关键词，匹配标题、关键词标签和记录 ID。留空则按时间倒序返回最近记录。 type: 可选，按类型过滤。常用值：decision / code_change / issue / note / reference。 limit: 最多返回条数，1–50，默认 10。

Returns: JSON：{ok, count, results:[{id, type, title, keywords, created_at, update_version}]} 拿到 id 后，如需全文再调 read_raw_data。

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": "search_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNo
limitNo
keywordNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.7/5.0
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 well: it discloses that results are summaries only, that an empty keyword yields reverse-chronological ordering, and the limit bounds (1–50, default 10). It does not mention permissions, scoping across workspaces/users, or whether the index is eventually consistent, which are the remaining behavioral gaps.

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 most decision-relevant fact (summaries, not raw text) and cleanly sectioned into Args/Returns. The Returns block partially duplicates the existing output schema, which is the only place a sentence doesn't fully earn its place.

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 3-param, zero-required search tool with no annotations, this covers purpose, ordering semantics, parameter ranges, and the next-step routing. An agent has everything needed to invoke it correctly and to know what to do with the returned ids.

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%, so the description must compensate and it does fully — keyword's match targets (title, keyword tags, record ID) plus its empty-value behavior, type's common values (decision/code_change/issue/note/reference) which the schema does not enumerate at all, and limit's range and default. Every parameter gains meaning the schema does not provide.

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+resource (检索记忆索引) and the exact shape of what comes back (摘要列表，不含原文), which immediately separates it from read_raw_data and save_memory. The scoping phrase '不含原文' is the key discriminator against the full-text sibling.

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 frames itself as '访问历史记忆的第一步' with a prohibition on skipping it, and then names the follow-up alternative: '拿到 id 后，如需全文再调 read_raw_data'. Both the when-to-use and the handoff condition are stated, leaving nothing 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