Search an initialized memory shelf for episodes containing all query tokens, returning addresses and snippets. Use it to locate episodes when the episode ID is unknown.
Grep the shelf for episodes matching every query token; returns addresses and snippets. Use when the episode id is unknown.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.3.0Input schema / $defs / SearchInput / additionalPropertiesAdded value: +falseInput schema / $defs / SearchInput / properties / shelf_path / defaultAdded value: +""Input schema / $defs / SearchInput / properties / shelf_path / descriptionPrevious value: -"Path to an initialized memory shelf."New value: +"Path to an initialized memory shelf. Optional: when omitted, the shelf named by $MEMSHELF_SHELF_PATH is used. Pass it explicitly to address a different shelf than that default."Input schema / $defs / SearchInput / requiredPrevious value: -[
- "shelf_path",
- "query"
-]New value: +[
+ "query"
+]v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare this a safe, idempotent, non-destructive read, so the safety profile is fully covered. The description adds the AND-token matching semantics and return shape, which is modest extra value, but says nothing about result limits, ranking, or empty-match behavior.
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 tightly written clauses with zero filler; the retrieval semantics and the usage trigger are both 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?
An output schema exists so return values need not be explained, and the core search behavior and trigger condition are present. The one gap is max_results, whose default of 10 and effect on results is never described anywhere.
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 schema itself documents query (space-separated tokens, all must hit) and shelf_path (env-var default), so the description's restatement of token-AND matching is largely redundant. max_results carries no description in the schema and none here, leaving one parameter's semantics unexplained.
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 (grep/search), resource (episodes on the shelf) and the matching rule (every query token), plus what it returns (addresses and snippets). It is clear on its own but never names a sibling, so an agent must infer the boundary with memshelf_recall/resolve rather than being told.
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?
"Use when the episode id is unknown" gives an explicit trigger condition and implicitly routes the agent away from id-based lookups. It stops short of naming the alternative tool (e.g. memshelf_recall) or stating when this search should NOT be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.