haus

recall_memory

Recall long-term memories stored about the current household. Call this at the start of advisory or open-ended turns. Filter by type when only one author's notes are relevant.

Input Schema

TableJSON Schema

Name	Required	Description
`type`	No	Filter by author. Omit for both.
`limit`	No	Max number of memories to return in this page. 1-100, default 20.
`cursor`	No	nextCursor from a previous response. Omit for the first page.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`items`	Yes
`title`	No
`message`	No
`variant`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 8, 2026

changedInput schema / properties / cursor / description

Previous value: -"Pagination cursor: pass back the nextCursor value from a prior recall_memory response to fetch the next page. Omit to start from the first page."New value: +"nextCursor from a previous response. Omit for the first page."

changedInput schema / properties / type / description

Previous value: -"Optional filter: 'system' for memories you (the agent) wrote, 'user' for memories the user stated. Omit to return both."New value: +"Filter by author. Omit for both."

Changed6 schema fields changedJul 14, 2026

addedInput schema / examples

Added value: +[
+  {
+    "limit": 20,
+    "type": "user"
+  }
+]

changedInput schema / properties / cursor / description

Previous value: -"Pagination cursor from a prior call"New value: +"Pagination cursor: pass back the nextCursor value from a prior recall_memory response to fetch the next page. Omit to start from the first page."

addedInput schema / properties / cursor / examples

Added value: +[
+  "eyJQSyI6IkhvdXNlaG9sZCMxMjM0In0="
+]

changedInput schema / properties / limit / description

Previous value: -"1-100, default 20"New value: +"Max number of memories to return in this page. 1-100, default 20."

addedInput schema / properties / limit / examples
```
Added value: +[
+  20
+]
```
addedInput schema / properties / type / examples
```
Added value: +[
+  "user"
+]
```

First observedJun 30, 2026

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint=false and destructiveHint=false, the annotations provide no positive safety guarantee, so the description must carry the behavioral burden. It adds useful scoping/filter behavior, but does not clarify whether recall has side effects on memory state; there is no direct contradiction, only ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and scope, and the second sentence packs both timing and filter guidance without redundancy. Every word contributes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is sufficient for a low-complexity retrieval tool with a rich schema and output schema, covering when and how to scope the call. It could be slightly more complete by naming the sibling write tools as alternatives, but nothing essential is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes all three parameters with 100% coverage, so the baseline applies. The description adds a small decision rule for the type parameter, but does not add meaning beyond what the schema already provides for limit and cursor.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb ("Recall"), a specific resource (long-term memories), and a scope (the current household), which distinguishes it from sibling memory tools like store_memory, update_memory, and forget_memory. The behavior is immediately identifiable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit timing cue (start of advisory or open-ended turns) and a filtering condition (when only one author's notes are relevant). It does not spell out exclusions or alternatives, but the context is clear enough for an agent to know when to call it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All haus tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?