Retrieves past events and user statements from the event layer using semantic search, returning the most relevant memories when specific details are needed.
在事件层里按语义检索旧事（用户说过的话、被记下的关键事件）。用于需要具体细节时；核心印象层不通过这个工具暴露。
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | 最多返回几条，默认 6 | |
| query | Yes | 要找什么，用自然语言 |
Changes observed during successful MCP inspections.
v0.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It discloses the layer boundary and what is intentionally not exposed, which is useful behavioral context. However, it says nothing about the shape of results, whether matches are ranked or include timestamps/snippets, or how the 'k' cap interacts with ranking — gaps that matter for a retrieval tool with no output schema.
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, front-loaded with the core retrieval action and layer scope, followed by the usage cue. No filler. Slightly terse for the behavioral information an unannotated tool should convey, but structurally sound.
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 low-complexity, 2-parameter retrieval tool this covers purpose, layer scope, and usage trigger, which is largely adequate. With no annotations and no output schema, though, the description is the only place an agent could learn what a result looks like (event text, relevance, timestamps) and it omits that.
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%: 'query' is documented as natural language and 'k' as max results with a default of 6. The description adds no parameter-level detail beyond this, so the baseline 3 is appropriate.
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: 'semantic search of old events at the event layer' (按语义检索旧事), with a concrete scope (things the user said, recorded key events). It also distinguishes its layer from the 'core impression layer', making it identifiable relative to the memory-siblings. It stops short of naming a specific sibling tool, so a 4 rather than 5.
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?
'用于需要具体细节时' gives a clear usage condition, and '核心印象层不通过这个工具暴露' implicitly routes impression-level queries to another tool. That is a genuine boundary for tool selection. It does not explicitly name the alternative sibling or give when-not-events scenarios, so not a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.