Archive a conversation transcript into a local memory store so other agents can search and replay it later.
归档一次对话原文（会话层）。把当前对话保存进本地库，其他 Agent 之后可检索复现
| Name | Required | Description | Default |
|---|---|---|---|
| agent | No | 来源 Agent 名 | |
| title | No | 会话标题（留空按首句自动生成） | |
| project | No | 所属项目 | |
| summary | No | 一句话摘要（可选） | |
| transcript | Yes | 整段对话文本（或 JSONL/JSON 数组） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With zero annotations the description carries the full burden. It does disclose the essential behavior — the transcript is persisted into a local library and later retrievable by other agents — but says nothing about overwrite/duplicate semantics, required permissions, title auto-generation side effects, or failure modes for a write tool.
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?
Two short sentences, zero padding, with the action and scope front-loaded. Efficient, though the second sentence mostly restates persistence already implied by 归档.
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?
No output schema and no annotations, so the description must cover return/behavior on its own. It conveys persistence and retrievability but omits return values, conflict handling, and the save-vs-memory routing decision, leaving gaps for a 5-parameter write tool.
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 all five parameters including the transcript format hint (JSONL/JSON array). The description adds no parameter-level detail beyond what the schema provides, 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?
States a specific verb (归档/保存) and resource (对话原文, 会话层), and distinguishes scope from the memory_* siblings by naming the session layer. It even hints at the read counterpart ('其他 Agent 之后可检索复现'), though it does not name session_recall explicitly.
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?
No explicit when-to-use, no exclusions, and no comparison to memory_save, which is the obvious confusing sibling since both persist content. The '会话层' phrasing implies a session-vs-memory distinction but leaves the agent to infer it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.