Search memories stored in DeepMemory using semantic search. Returns the most relevant memories for the given query, ranked by hybrid scoring (vector similarity + BM25 keyword match + entity boost + time decay).
Use this to retrieve context from past conversations before responding to the user. Memories are scoped to the user_id provided during write.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| top_k | No | ||
| api_key | No | ||
| user_id | No | default | |
| threshold | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses the hybrid scoring mechanism (vector similarity, BM25, entity boost, time decay) and scoping behavior, which goes beyond the bare schema. It does not explicitly state read-only nature or discuss rate limits, but the read behavior is implied and the scoring detail is valuable.
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?
Three sentences, zero fluff, front-loaded with the primary action. Each sentence adds value: purpose, scoring, usage context, and scoping. Efficient and well-structured.
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 purpose, scoring, usage, and scoping. However, with no output schema, it does not specify the return format (e.g., list of memory IDs, scores, text). Given 5 parameters and no annotations, it is decent but not fully complete; it could mention the return structure to aid the agent. It is adequate for a search tool but leaves some ambiguity.
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 0%, so the description must explain parameters. It implicitly covers 'query' (given query) and 'user_id' (scoping), but does not explain 'top_k', 'threshold', or 'api_key'. The parameter names are self-explanatory, but the description does not add meaningful detail beyond the schema's defaults, leaving the agent to guess on threshold semantics.
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 clearly states the tool searches memories with semantic search and returns ranked results. It distinguishes from sibling 'deepmem_write' by focusing on retrieval rather than storage, and explicitly says to use it for context from past conversations.
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?
Provides explicit usage guidance: 'Use this to retrieve context from past conversations before responding to the user.' It also notes memory scoping to user_id, implying the need to pass the correct user_id. However, it does not mention when not to use it or alternative approaches, but the sibling-tool context makes the primary use case clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The two tools have completely distinct purposes: one searches existing memories, the other writes new ones. No overlap or ambiguity exists between them.
Both tools follow a consistent pattern: 'deepmem_' prefix plus a verb (search, write). This is uniform and predictable.
With only 2 tools, the server is minimal but covers its core purpose of memory storage and retrieval. It feels slightly sparse but is not inappropriate for a focused memory server.
The server covers the essential lifecycle of memories: writing and searching. However, there is no explicit delete or update operation, which are minor gaps for a persistence layer.