Search memories by namespace with optional text query.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Optional search query (substring match) | |
| limit | No | Max results to return (default 50, max 200) | |
| namespace | Yes | Namespace to search in |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral characteristics. It only states what the tool does (searches) but does not explicitly state that it is a read-only operation, what it returns (e.g., matching memories), or any details about ordering, pagination, or error behavior. The absence of this information leaves significant room for interpretation.
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?
The description is a single, front-loaded sentence that states the verb, resource, and key parameters. It contains no redundant information and is immediately scannable, earning maximum 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?
For a simple search tool with three well-documented parameters and no output schema, the description provides the essential context (search by namespace, optional text query). While it lacks some behavioral details like return format, the schema covers parameter semantics, making it adequately complete for this straightforward tool. The lack of an output schema means some return-value explanation would be helpful, but it is not critical.
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?
The input schema provides complete descriptions for all three parameters (namespace, q, limit) with 100% coverage. The description adds minimal semantic value beyond the schema, only referring to 'optional text query' which matches the 'q' parameter description. Since the schema already does the heavy lifting, a 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 identifies the action ('Search') and the target resource ('memories'), and specifies the key scoping attribute ('by namespace') and the optional filter ('text query'). This clearly differentiates it from sibling tools like clear_namespace, delete_memory, get_memory, and store_memory, which perform different operations on memories.
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 searching within a specific namespace, but it does not provide explicit guidance on when to choose this tool over alternatives like get_memory (which likely retrieves a single memory by ID). There is no mention of when not to use it or a named alternative, so it only provides minimal implied context.
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.
Each tool has a clearly distinct purpose: store, retrieve by ID, search, delete by ID, and clear a namespace. No two tools overlap in functionality or target different granularities.
All tool names follow a consistent verb_noun pattern with clear verbs (store, get, search, delete, clear) and nouns (memory, memories, namespace). The slight pluralization in search_memories is natural and does not disrupt consistency.
Five tools is a well-scoped set for an agent memory system, covering the essential operations without unnecessary bloat or redundancy.
The surface covers create (store), read (get, search), and delete (delete, clear) for memories. A direct update operation is missing, but users can work around it by deleting and re-storing, so the gap is minor.