Semantically search a memory collection (namespace) and return the most relevant stored entries. The retrieval half of RAG.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural-language query; returns the most semantically similar stored entries. | |
| top_k | No | How many results to return (default 5). | |
| namespace | Yes | The namespace to search within (the same key used on upsert). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It indicates a read-only semantic search, which is clear, but it does not mention any potential side effects, rate limits, or authentication requirements. The description minimally addresses behavioral traits.
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 sentences with no wasted words. The key purpose and context (RAG retrieval half) are front-loaded. Every sentence adds value.
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 simple search tool with no output schema, the description adequately states that it returns relevant stored entries. It covers the essential behavior given the parameter richness and sibling context, but could mention result format or pagination.
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 the input schema already documents all parameters. The description adds minor context (e.g., 'natural-language query') but does not significantly enhance understanding beyond the schema. Baseline score of 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 clearly states the verb ('search'), resource ('memory collection/namespace'), and distinguishes from the sibling tool 'memory_upsert' by calling it 'the retrieval half of RAG'. This directly differentiates from the write operation.
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 implies usage for reading via 'retrieval half of RAG', but it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion criteria or context for when not to use it.
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 for storing data and one for retrieving it. There is no ambiguity or overlap.
Both tools follow a consistent verb_noun pattern (memory_search and memory_upsert) using the same prefix and clear action words.
Two tools is minimal but perfectly appropriate for a focused memory server covering the essential store and retrieve operations. It could benefit from a delete tool but is not over- or underwhelming.
The core RAG operations (store and retrieve) are covered. Missing a delete or list all tool is a minor gap, but the main workflow is complete for typical use.