Memoreei

search_memoreei

Read-only

Search the owner's messages by meaning and by keyword, best match first.

Instructions

Search the owner's messages by meaning and by keyword, best match first.

Every filter narrows the search before it ranks anything, so a filtered search finds the best matches within those messages. If results is empty or note is set, note says why and what to try.

Input Schema

Name	Required	Description	Default
`after`	No	Only messages on or after this date: 'YYYY-MM-DD' or 'YYYY-MM-DDTHH:MM', in the owner's time zone.
`limit`	No	How many results. Default 10.
`query`	Yes	What to look for, in a few words: 'credit card recommendation', 'dinner Saturday'. Leave people's names out; use participant for who.
`before`	No	Only messages on or before this date: 'YYYY-MM-DD' (the whole day counts) or 'YYYY-MM-DDTHH:MM'.
`source`	No	Only one app ('imessage', 'whatsapp', 'signal', …) or one chat, by a result's source. For a person, use participant instead.
`participant`	No	Whose messages to search: a name ('Jane Doe'), part of one ('Jane', 'jan do'), a phone number in any format ('+1 202 555 0142', '2025550142') or an email address. One name finds the person on every app; 'me' is the owner.
`participant_scope`	No	How much of participant's messages to search. 'conversation' (default): what they wrote anywhere, plus both sides of the owner's one-to-one chats with them. 'sent': only what they wrote. 'any_chat': everything in every chat they are in, groups included.	conversation

Output Schema

Name	Required	Description	Default
`note`	No
`people`	No
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed16 schema fields changedv0.4.7Oct 14, 2026

addedInput schema / properties / after / description

Added value: +"Only messages on or after this date: 'YYYY-MM-DD' or 'YYYY-MM-DDTHH:MM', in the owner's time zone."

addedInput schema / properties / before / description

Added value: +"Only messages on or before this date: 'YYYY-MM-DD' (the whole day counts) or 'YYYY-MM-DDTHH:MM'."

addedInput schema / properties / limit / description
```
Added value: +"How many results. Default 10."
```
addedInput schema / properties / limit / maximum
```
Added value: +100
```
addedInput schema / properties / limit / minimum
```
Added value: +1
```

addedInput schema / properties / participant / description

Added value: +"Whose messages to search: a name ('Jane Doe'), part of one ('Jane', 'jan do'), a phone number in any format ('+1 202 555 0142', '2025550142') or an email address. One name finds the person on every app; 'me' is the owner."

addedInput schema / properties / participant_scope

Added value: +{
+  "default": "conversation",
+  "description": "How much of participant's messages to search. 'conversation' (default): what they wrote anywhere, plus both sides of the owner's one-to-one chats with them. 'sent': only what they wrote. 'any_chat': everything in every chat they are in, groups included.",
+  "enum": [
+    "conversation",
+    "sent",
+    "any_chat"
+  ],
+  "title": "Participant Scope",
+  "type": "string"
+}

addedInput schema / properties / query / description

Added value: +"What to look for, in a few words: 'credit card recommendation', 'dinner Saturday'. Leave people's names out; use participant for who."

addedInput schema / properties / source / description

Added value: +"Only one app ('imessage', 'whatsapp', 'signal', …) or one chat, by a result's source. For a person, use participant instead."

addedOutput schema / $defs

Added value: +{
+  "Message": {
+    "properties": {
+      "chat": {
+        "description": "The group's name, or the other person in a one-to-one chat",
+        "title": "Chat",
+        "type": "string"
+      },
+      "content": {
+        "description": "The message, as stored: usually 'sender: text'",
+        "title": "Content",
+        "type": "string"
+      },
+      "date": {
+        "description": "When it was sent, YYYY-MM-DD HH:MM, owner's time zone",
+        "title": "Date",
+        "type": "string"
+      },
+      "deleted": {
+        "description": "Deleted for everyone after it was read",
+        "title": "Deleted",
+        "type": "boolean"
+      },
+      "group": {
+        "description": "True for a group chat",
+        "title": "Group",
+        "type": "boolean"
+      },
+      "hit": {
+        "description": "The message get_context was asked about",
+        "title": "Hit",
+        "type": "boolean"
+      },
+      "id": {
+        "description": "Pass to get_context to read around this message",
+        "title": "Id",
+        "type": "string"
+      },
+      "platform": {
+        "description": "imessage, whatsapp, signal, …",
+        "title": "Platform",
+        "type": "string"
+      },
+      "sender": {
+        "description": "Who wrote it; 'me' is the owner",
+        "title": "Sender",
+        "type": "string"
+      },
+      "source": {
+        "description": "The chat's id, for the source filter",
+        "title": "Source",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "date",
+      "platform",
+      "chat",
+      "group",
+      "sender",
+      "content",
+      "source"
+    ],
+    "title": "Message",
+    "type": "object"
+  },
+  "PersonMatch": {
+    "properties": {
+      "identifiers": {
+        "description": "Phone numbers and addresses known for them",
+        "items": {
+          "type": "string"
+        },
+        "title": "Identifiers",
+        "type": "array"
+      },
+      "me": {
+        "description": "This is the owner",
+        "title": "Me",
+        "type": "boolean"
+      },
+      "name": {
+        "title": "Name",
+        "type": "string"
+      }
+    },
+    "required": [
+      "name",
+      "identifiers"
+    ],
+    "title": "PersonMatch",
+    "type": "object"
+  }
+}

addedOutput schema / properties / note

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Note"
+}

addedOutput schema / properties / people

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "$ref": "#/$defs/PersonMatch"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "People"
+}

removedOutput schema / properties / result

Removed value: -{
-  "items": {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  "title": "Result",
-  "type": "array"
-}

addedOutput schema / properties / results

Added value: +{
+  "items": {
+    "$ref": "#/$defs/Message"
+  },
+  "title": "Results",
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "results"
+]

changedOutput schema / title

Previous value: -"search_memoreeiOutput"New value: +"SearchResult"

Addedv0.4.4Oct 3, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), but the description adds genuine behavioral context: results are ranked best-match-first, filters are applied before ranking, and the failure/empty path surfaces an explanatory 'note'. It stops short of mentioning pagination or result-size behavior, but the filter-then-rank ordering and empty-result semantics are substantive additions.

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

Conciseness4/5

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

Three sentences, front-loaded with the core capability, and no filler. The final sentence ('If results is empty or note is set, note says why and what to try') is slightly convoluted in phrasing but each sentence carries distinct content.

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?

An output schema exists, so return-value explanation is not required, and the description still cues the 'results'/'note' structure it returns. For a 7-parameter read-only search with full schema coverage, the definition supplies the retrieval semantics an agent needs; only cross-tool routing guidance is absent.

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?

Schema description coverage is 100%, so every parameter (after, before, source, participant, participant_scope, limit, query) is already documented in the schema, including examples and the enum semantics. The description only speaks of 'filters' generically and adds no syntax or constraint detail beyond the schema. Baseline 3 applies.

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?

States a specific verb and resource ('Search the owner's messages') and even names the retrieval mode ('by meaning and by keyword, best match first'). No sibling in the tool list performs search, so the purpose is unambiguous without needing to reference an alternative.

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

Usage Guidelines3/5

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

The description explains result/empty behavior ('If results is empty or note is set, note says why and what to try') but never states when to choose this over other tools or any precondition. Usage is implied by the search framing rather than explicitly guided. With a sibling set consisting only of sync/import/add tools, the lack of explicit alternatives is a smaller gap but still a gap.

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