Skip to main content
Glama

recall

Searches earlier chat notes by meaning, surfacing related ideas even when wording differs. With no query, shows recent notes to orient a new conversation.

Instructions

Finds notes kept in earlier chats, by meaning: 'budget priorities' finds a note about 'retention focus, $40K' though the words differ. With no query it shows the most recent notes, which is a quick way to see what is already known when a conversation starts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNoIf true, searches every folder and shows each result's address. Use it when you don't know which folder holds something.
fullNoIf true, returns full content of each memory. Default false (gist summaries only).
grepNoOptional. Exact words to find, case-blind, in the FULL content: returns the matching lines, not whole memories. Use it to see every line that holds a name, a number or anything you know verbatim: a query shows the best matches, this shows every match up to the limit (50 lines unless you raise it). A list means every term must appear in the memory. Combines with since/until and thread.
imageNoOptional. The ID or address of an image, as shown after 'image' on a result line (for example 1B2C3D4E). Returns that image itself, to look at, with its size and the notes that show it, instead of searching. Looking at one costs about 1,700 tokens.
limitNoMaximum results. Default 10.
queryNoWhat you are looking for. A topic, a name, a concept. One search reads it two ways together: by meaning, so related memories are found even when the words differ, and by its words, so specific terms are found too. There is no mode to choose. Proper names (a Capitalized word after the first, or anything in "quotes") must match exactly, and memories holding them come first. An address like 13625F6B:3487B9B0 opens that memory, whichever folder it is in. Leave it out to get the most recent memories, which is how to orient yourself at the start of a conversation.
sinceNoOptional. Only memories from this time on: '24h', '7d', '2w', a date ('2026-09-23'), a local time ('2026-09-23 14:00') or RFC 3339. Use it whenever the question has a time in it ('last week', 'yesterday'). Without it, older memories outrank recent ones.
untilNoOptional. Only memories before this time. Same forms as since; a date includes that whole day.
folderNoWhich folder to read, by name or 8-character ID. Choose one with the folders tool. Left out, this reads the folder set for where you were started (a .geniuz-folder file or GENIUZ_DB), else My memory. An unknown name is an error, never a different folder.
threadNoOptional. The short UUID or address of any memory in a thread (the 8 characters before '|', or the one after '<-'). Returns that whole thread, root first, oldest to newest, instead of searching. Use it to read a conversation you found one piece of.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.1.7
    • changedInput schema / properties / grep / description
      Previous value: -"Optional. Exact words to find, case-blind, in the FULL content: returns the matching lines, not whole memories. Use it for names, numbers and anything you know verbatim (semantic search does not find proper names reliably). A list means every term must appear in the memory. Combines with since/until and thread."New value: +"Optional. Exact words to find, case-blind, in the FULL content: returns the matching lines, not whole memories. Use it to see every line that holds a name, a number or anything you know verbatim: a query shows the best matches, this shows every match up to the limit (50 lines unless you raise it). A list means every term must appear in the memory. Combines with since/until and thread."
    • changedInput schema / properties / query / description
      Previous value: -"What you are looking for. A topic, a name, a concept. Semantic search finds related memories even if the exact words differ. Proper names (a Capitalized word after the first, or anything in \"quotes\") must match exactly, and memories holding them come first. An address like 13625F6B:3487B9B0 opens that memory, whichever folder it is in. Leave it out to get the most recent memories, which is how to orient yourself at the start of a conversation."New value: +"What you are looking for. A topic, a name, a concept. One search reads it two ways together: by meaning, so related memories are found even when the words differ, and by its words, so specific terms are found too. There is no mode to choose. Proper names (a Capitalized word after the first, or anything in \"quotes\") must match exactly, and memories holding them come first. An address like 13625F6B:3487B9B0 opens that memory, whichever folder it is in. Leave it out to get the most recent memories, which is how to orient yourself at the start of a conversation."
  2. Changed1 schema field changedv5.1.2
    • addedInput schema / properties / image
      Added value: +{
      +  "description": "Optional. The ID or address of an image, as shown after 'image' on a result line (for example 1B2C3D4E). Returns that image itself, to look at, with its size and the notes that show it, instead of searching. Looking at one costs about 1,700 tokens.",
      +  "type": "string"
      +}
  3. Changed2 schema fields changedv5.0.11
    • changedInput schema / properties / folder / description
      Previous value: -"Which folder to use, by name or 8-character ID. Choose one with the folders tool. Left out, this uses the current folder. An unknown name is an error, never a different folder."New value: +"Which folder to read, by name or 8-character ID. Choose one with the folders tool. Left out, this reads the folder set for where you were started (a .geniuz-folder file or GENIUZ_DB), else My memory. An unknown name is an error, never a different folder."
    • changedInput schema / properties / since / description
      Previous value: -"Optional. Only memories from this time on: '24h', '7d', '2w', a date ('2026-09-23'), a local time ('2026-09-23 14:00') or RFC 3339. Use it whenever the question has a time in it ('last week', 'yesterday') — without it, older memories outrank recent ones."New value: +"Optional. Only memories from this time on: '24h', '7d', '2w', a date ('2026-09-23'), a local time ('2026-09-23 14:00') or RFC 3339. Use it whenever the question has a time in it ('last week', 'yesterday'). Without it, older memories outrank recent ones."
  4. Changed4 schema fields changedv5.0.1
    • addedInput schema / properties / all
      Added value: +{
      +  "description": "If true, searches every folder and shows each result's address. Use it when you don't know which folder holds something.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / folder
      Added value: +{
      +  "description": "Which folder to use, by name or 8-character ID. Choose one with the folders tool. Left out, this uses the current folder. An unknown name is an error, never a different folder.",
      +  "type": "string"
      +}
    • changedInput schema / properties / query / description
      Previous value: -"What you are looking for. A topic, a name, a concept. Semantic search finds related memories even if the exact words differ. Proper names (a Capitalized word after the first, or anything in \"quotes\") must match exactly, and memories holding them come first. Required unless thread is given."New value: +"What you are looking for. A topic, a name, a concept. Semantic search finds related memories even if the exact words differ. Proper names (a Capitalized word after the first, or anything in \"quotes\") must match exactly, and memories holding them come first. An address like 13625F6B:3487B9B0 opens that memory, whichever folder it is in. Leave it out to get the most recent memories, which is how to orient yourself at the start of a conversation."
    • changedInput schema / properties / thread / description
      Previous value: -"Optional. The short UUID of any memory in a thread (the 8 characters before '|', or the one after '<-'). Returns that whole thread, root first, oldest to newest, instead of searching. Use it to read a conversation you found one piece of."New value: +"Optional. The short UUID or address of any memory in a thread (the 8 characters before '|', or the one after '<-'). Returns that whole thread, root first, oldest to newest, instead of searching. Use it to read a conversation you found one piece of."
  5. Changed6 schema fields changedv4.1.1
    • addedInput schema / properties / grep
      Added value: +{
      +  "description": "Optional. Exact words to find, case-blind, in the FULL content: returns the matching lines, not whole memories. Use it for names, numbers and anything you know verbatim (semantic search does not find proper names reliably). A list means every term must appear in the memory. Combines with since/until and thread.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": [
      +    "string",
      +    "array"
      +  ]
      +}
    • changedInput schema / properties / query / description
      Previous value: -"What you are looking for. A topic, a name, a concept. Semantic search finds related memories even if the exact words differ."New value: +"What you are looking for. A topic, a name, a concept. Semantic search finds related memories even if the exact words differ. Proper names (a Capitalized word after the first, or anything in \"quotes\") must match exactly, and memories holding them come first. Required unless thread is given."
    • addedInput schema / properties / since
      Added value: +{
      +  "description": "Optional. Only memories from this time on: '24h', '7d', '2w', a date ('2026-09-23'), a local time ('2026-09-23 14:00') or RFC 3339. Use it whenever the question has a time in it ('last week', 'yesterday') — without it, older memories outrank recent ones.",
      +  "type": "string"
      +}
    • addedInput schema / properties / thread
      Added value: +{
      +  "description": "Optional. The short UUID of any memory in a thread (the 8 characters before '|', or the one after '<-'). Returns that whole thread, root first, oldest to newest, instead of searching. Use it to read a conversation you found one piece of.",
      +  "type": "string"
      +}
    • addedInput schema / properties / until
      Added value: +{
      +  "description": "Optional. Only memories before this time. Same forms as since; a date includes that whole day.",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "query"
      -]
  6. First observedv4.0.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does disclose the key non-obvious behavior: hybrid meaning-plus-word matching, exact-match precedence for proper names, address-based direct open, and recency default when no query is given. It stops short of stating that the operation is read-only or describing the result-line format, which the schema only alludes to.

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 core capability, and the example ('budget priorities' → 'retention focus, $40K') earns its place by making the semantic behavior concrete. No filler.

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?

For a 10-parameter tool with no annotations and no output schema, the description covers the essential retrieval semantics and the default path, and the schema handles the rest. The main gap is that nothing in the description explains what a result looks like, which matters when there is no output schema.

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 coverage is 100%, so every parameter is already documented in detail. The description adds only the semantic framing of 'query' and the no-query default, which is a modest supplement rather than new meaning beyond the schema.

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 ('Finds notes kept in earlier chats') and immediately qualifies the retrieval mode ('by meaning'), with a concrete example showing why semantic matching matters. It also covers the zero-argument behavior, so an agent knows what the tool does with and without a query.

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?

Gives a clear when-to-use case for the empty-query path ('a quick way to see what is already known when a conversation starts'), and the folder parameter points at the sibling 'folders' tool for selection. It does not state when to prefer this over 'keep' or any exclusion, so guidance is clear but not complete.

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

Deploy Server

Other Tools