Retrieve relevant past experiences from long-term memory using a query, returning titles, summaries, tags, and importance scores to provide context and continuity.
在 PASM 长期记忆里检索与 query 相关的经历，返回标题/摘要/标签/重要度。
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | 返回条数，默认 5 | |
| query | Yes | 检索词 | |
| 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 the return fields but says nothing about result ordering, behavior when no matches exist, how the k limit applies, or agent_id scoping — significant gaps for a retrieval tool with zero annotation coverage.
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?
A single efficient sentence that front-loads the action and names the return fields. No wasted words, though it leans terse and could incorporate usage guidance without losing conciseness.
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?
Medium complexity tool with 3 params, no output schema, and no annotations. The description names return fields, which helps, but omits ordering, empty-result behavior, and how it differs from pasm_semantic — leaving an agent somewhat under-informed about call outcomes.
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 coverage is 67% and all three parameters (query, k, agent_id) have descriptions in the schema itself. The description adds the return-format meaning but does not clarify parameter semantics beyond what the schema already states; the moderate coverage means it neither needs to fully compensate nor is it redundant.
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 states a specific action (检索/retrieve from PASM long-term memory) and names the output fields (title/summary/tags/importance). It clearly conveys what the tool does, though it doesn't explicitly differentiate itself from the closely related sibling pasm_semantic.
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 guidance on when to use recall vs. the alternative pasm_semantic (likely a semantic/search variant). No mention of prerequisites or conditions for use, leaving the agent to infer its role from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.