Search stored memory observations with FTS5 queries and get compact snippets to reduce context tokens. Filter by project or type.
Layer 2 FTS5 search over memory observations, compact rows with snippets (~60 tokens/result).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Default 20. | |
| query | Yes | FTS5 (AND/OR/NOT/phrase). | |
| project | No | Project name/path (default: active). | |
| type_filter | No |
Changes observed during successful MCP inspections.
v4.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful output-shape context ('compact rows with snippets, ~60 tokens/result') that helps the agent budget results, but says nothing about ordering, pagination, or result count 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?
A single front-loaded sentence with no filler, efficiently conveying mechanism and result shape. Slightly terse relative to the ambiguity in the sibling landscape, but well-structured.
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 output schema, the description should carry return-value burden; it partially does by noting compact rows, snippets, and token cost, but omits ordering and result fields. For a search tool with 4 params and no output schema, this is adequate but leaves gaps.
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 75%, with the FTS5 query syntax and defaults documented in the schema itself. The description adds no parameter detail and leaves type_filter (the uncovered 25%) undocumented in both places, so it neither compensates nor detracts.
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 (search) and resource (memory observations), qualified by 'Layer 2 FTS5', which is concrete enough to identify the mechanism. However, it does not distinguish itself from the many other search siblings (reasoning_search, capture_search, ts_search, search_codebase), so the agent must infer scope from the name alone.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. Given the crowded sibling set of search tools, the absence of routing guidance is a real gap; usage is only weakly implied by the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.