Search saved memory records by keyword to return ranked matches, so agents can recall relevant context by query with optional scope and result limit.
Full-text (keyword) search of whole memories. Returns ranked matches.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 10). | |
| query | Yes | ||
| scope | No |
Changes observed during successful MCP inspections.
v2.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the full burden. It notes keyword (not semantic) matching and ranked results, which is some signal, but says nothing about pagination, ranking basis, scope behavior, or whether scope filters by workspace/user.
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 tight sentences, no waste, and the matching mode is front-loaded.
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?
A search tool with no annotations, no output schema, and two of three parameters undocumented. Missing scope semantics and the ranking/return shape leaves real ambiguity for correct invocation.
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 33% — only 'limit' is described. 'query' and 'scope' are undocumented in both schema and description, so the meaning of 'scope' (workspace? user? memory type?) is entirely left to inference.
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 ('Full-text (keyword) search of whole memories') and distinguishes the search mode (keyword rather than semantic, implied by contrast with memory_recall). Doesn't explicitly differentiate from memory_recall or memory_get by name.
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 when-to-use guidance. With siblings like memory_recall (likely semantic/associative) and memory_get (likely direct retrieval), an agent must guess which retriever fits a given need.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.