Search long-term memories semantically to retrieve past context relevant to a query.
Semantically search long-term memories relevant to a query. This is how you remember past context.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| top_k | No | ||
| min_score | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does not state that this is a read-only operation, how results are ranked or capped (top_k max 30), what min_score filters, or whether recall touches persistent state. Only the bare 'search' semantics are conveyed.
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 with the core operation front-loaded and no wasted clauses. The second sentence is a little fluffy but functions as usage framing rather than filler.
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 no annotations, no output schema, and three entirely undocumented parameters, the description leaves too much to inference for a search tool. It never describes the shape of a returned memory or how scores are surfaced to the caller.
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% for all three parameters, so nothing documents that top_k is the result count or that min_score is a similarity threshold. The phrase 'relevant to a query' hints at a relevance cutoff but never explains min_score's scale or how it interacts with top_k.
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 verb and resource: semantic search over long-term memories. That distinguishes it from keyed siblings like memory_get and memory_list, but it never names those alternatives, so the differentiation is implicit rather than explicit.
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?
"This is how you remember past context" implies the recall use case, which is genuine guidance about when to reach for it. However, it offers no exclusions and does not distinguish it from memory_context, knowledge_search, or retrieve_exemplars, all of which an agent might plausibly pick instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.