Search stored memories by exact keyword substring match, with optional category filter to locate specific information.
Search memories by keyword (exact substring match). For semantic search, use recall with op:similar or op:fuse.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Search keyword | |
| category | No | Limit to category |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and it makes a meaningful disclosure: searches are exact substring matches, which prevents the agent from assuming semantic or fuzzy behavior. It also signals that semantic variants belong to recall. It doesn't mention case sensitivity, ordering, or pagination, but those are secondary for a simple search tool.
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 no filler. The primary matching behavior is front-loaded, and the alternative is given only after the core purpose is clear. Every phrase contributes to selection or invocation.
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 low-complexity tool with one required parameter, the description plus schema is sufficient to invoke it correctly and to avoid the main confusion with recall. It does omit the return shape and any result-limiting behavior, but those are not critical for basic use given the simple signature.
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 both parameters are already documented in the schema. The description adds value mainly by clarifying that `keyword` is matched as an exact substring, but it doesn't elaborate on `category` beyond the schema's 'Limit to category.' This meets the baseline without going beyond it.
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 names a specific verb and resource ('Search memories') and immediately qualifies the core behavior as an 'exact substring match.' This distinguishes it from the semantic recall sibling without requiring the agent to inspect either schema.
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 second sentence explicitly states when not to use this tool: 'For semantic search, use recall with op:similar or op:fuse.' This gives the agent a clear routing rule and names the exact alternative operations, leaving no ambiguity about which tool handles fuzzy/semantic queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.