Retrieve a small set of highly relevant memories for the current query or topic, so AI assistants can recall useful context without loading all history.
按当前话题召回相关记忆（只返回少量高度相关的，不返回全部历史）。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 当前用户说的话或话题 | |
| top_k | No | 最多返回几条，默认 5 | |
| profile | No | 角色/用户分区，默认 default |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose a genuine behavioral trait — result set is deliberately truncated to a few highly relevant items rather than full history — but says nothing about ranking method, permissions, or response shape for a read tool with a 3-param surface.
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?
One compact sentence that front-loads the action and parenthesizes the scope constraint. No filler, no restatement of the 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?
With 3 simple parameters, full schema coverage, and no output schema, the description supplies the one thing the schema cannot: that results are a small relevant subset, not history. Missing details like relevance ranking or whether results are deduplicated are minor at this complexity.
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 each parameter is already documented (query, top_k default 5, profile default 'default'). The description only adds the framing that query is the current topic, which is marginal value beyond the schema — 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 and resource ('召回相关记忆') plus a scoping constraint ('只返回少量高度相关的，不返回全部历史') that implicitly distinguishes it from sibling list-style tools such as memory_list. It stops short of naming an alternative sibling explicitly, so it lands at 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?
The phrase '按当前话题' implies the trigger condition (there is an active topic/query), but the description never states when to prefer this over memory_list, memory_wake, or memory_explain. Usage is inferable rather than instructed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.