Search shared long-term memories by keyword to recall stored notes; scope results to global entries plus one exact project when a project is provided.
Bounded lexical/full-text recall. With project, returns global and that exact project; without project, global only. Project selection is a relevance filter, not authorization.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| project | No | ||
| include_history | No | ||
| character_budget | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. The description still adds real value: it discloses that results are bounded, that project scoping includes global plus the exact project, and crucially that project is a relevance filter rather than an authorization boundary — a behavioral/security trait not in the schema.
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?
Three short sentences, front-loaded with the retrieval mode followed by the scoping rule and the authorization clarification. No filler.
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 5 parameters, 0% schema coverage, and no output schema, the description should carry the load but omits include_history and character_budget entirely and says nothing about result ordering or return shape. It is complete for the project parameter only.
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 0% across 5 parameters, so the description must compensate and largely does not. It explains the semantics of project well but leaves query, limit, include_history, and character_budget undocumented; "bounded" only faintly gestures at the budget/limit parameters.
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?
"Bounded lexical/full-text recall" states the retrieval mechanism, which is more specific than a bare verb, but it never names the resource (memories) or distinguishes this from the sibling search_nodes. An agent must infer the target corpus from the tool 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?
The description clearly explains the project-filter scoping rule, which is genuine usage guidance. However, it offers no when-to-use-vs-alternatives guidance against search_nodes, read_graph, or open_nodes, so the agent gets scope semantics but no routing signal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.