Processes user input through a complete memory loop: retrieves memories, renders a template reply, and stores the conversation. Returns template-based responses for quick validation or offline use.
走一次完整认知回路：检索记忆 → 渲染回复 → 把这次对话写进记忆。回复是模板渲染、非 LLM 生成，用于快速验证或纯离线场景；要自然语言效果请用 pasm_context 配合你自己的模型。
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | 用户输入 | |
| agent_id | No | default |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden of behavioral disclosure. It reveals that the tool reads memory, renders a template reply, and writes the conversation back into memory, which is a meaningful side-effect disclosure. It does not detail return format or memory-mutation consequences, but the main non-obvious behavior—non-LLM template rendering—is clearly disclosed.
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 description is a single compact sentence that front-loads the core behavior, then adds the key caveat and alternative routing. There is no filler or redundant restatement of the tool name.
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?
The description covers the full pipeline, the intended use cases, and the recommended sibling for natural-language output, which is enough for safe invocation with the required text parameter. The main gaps are the undocumented agent_id parameter and no information about what the rendered reply looks like, but these do not prevent correct basic usage.
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 only 50%, with agent_id entirely undocumented in both the schema and the description. The description adds no parameter-level guidance beyond the flow-level context; it never mentions agent_id or how it affects the cognitive loop. Since the description does not compensate for the missing schema coverage of agent_id, parameter semantics are weak.
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 behavior with a concrete pipeline: 检索记忆 → 渲染回复 → 写进记忆. It further differentiates this tool from the sibling by explicitly stating the reply is template-rendered, not LLM-generated, and points to pasm_context for natural language. This makes the tool's role in the sibling set unambiguous.
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?
The description explicitly states when to use this tool ('用于快速验证或纯离线场景') and when to use an alternative ('要自然语言效果请用 pasm_context 配合你自己的模型'). This is clear, actionable guidance that an agent can act on without inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.