Retrieve persistent and recent memories at the start of each conversation to share cross-agent context and avoid re-explaining decisions, preferences, and pitfalls.
获取常驻上下文包（建议每次对话开始时调用）：常驻记忆 + 近期重点记忆，一次拿齐跨 Agent 共享的上下文。输出顺序固定（常驻在前、近期在后），便于模型商前缀缓存命中、省 token
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 近期重点条数，默认8 | |
| branch | No | 可选：当前所在 Git 分支。**不传时自动读当前目录的 git 分支、并在末尾标出「（自动探测）」**；同分支的记忆排前面，其他分支降权但不隐藏。不能带换行/控制字符 | |
| project | No | 项目名（可选，留空返回全局） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses the output composition and deterministic ordering (resident first, recent after) and the token/cache motivation, but says nothing about permissions, side effects, behavior when no memory exists, or 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The purpose and the call recommendation are front-loaded, and the trailing parenthetical about output ordering and cache efficiency is compact. It is dense but every clause contributes; no filler sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a no-annotation read tool with three optional parameters and no output schema, the description covers what the tool returns (composition plus ordering) and when to call it. It is largely sufficient, with only minor gaps around edge-case behavior and result field details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents limit, branch (including auto-detection and branch-weighting behavior), and project thoroughly. The description adds no parameter-level detail beyond that, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource: retrieving a resident context package composed of resident memory plus recent key memories in one call. This distinguishes it functionally from the list/search siblings by emphasizing the bundled, cross-Agent shared payload. It does not, however, explicitly name any sibling it replaces or differs from.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives a clear trigger condition: '建议每次对话开始时调用' (recommended at the start of each conversation), which tells the agent when to reach for it. It stops short of naming alternatives (e.g., memory_list or memory_search) or stating when not to use it, so there is no exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.