Skip to main content
Glama

notes_recall

Read-onlyIdempotent

Recall notes from your notebook. By default returns only your own notes (all scopes, newest first). Pass filter_agent_id= to read another agent's notebook, or filter_agent_id="all" (or "*") to read across every agent in the workspace. Pass scope to narrow to global/thread/person. Each result includes agent_id and agent_name of the author.

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": "notes_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoRecall a specific note by key (searched across every memory_type).
limitNoMax notes (default 20, max 50). Newest first.
scopeNoOptional filter: workspace | agent | thread | person ('global' = agent). Omit for all scopes.
formatNo'full' (default) = the notes with their text; 'index' = one compact line per note across every memory_type (type, date, key, first 120 chars), the same index a hosted session gets at start. Read a line's details with key=.
memory_typeNoWhich kinds of notes: one of context | fact | feedback | summary | procedural, or a list. Default 'context' (a call with `key` reads every type).
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
scope_ref_idNoFilter by specific thread_id or person_id
filter_agent_idNoOptional. Omit to read your own notes (an agent: its notebook; a person over MCP: the whole workspace). Pass a numeric agent_id as a string (e.g. "57") to read another agent's notebook (read-only). Pass "all" or "*" to read across all agents in the workspace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / format
      Added value: +{
      +  "description": "'full' (default) = the notes with their text; 'index' = one compact line per note across every memory_type (type, date, key, first 120 chars), the same index a hosted session gets at start. Read a line's details with key=.",
      +  "enum": [
      +    "full",
      +    "index"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / key / description
      Previous value: -"Recall a specific note by key"New value: +"Recall a specific note by key (searched across every memory_type)."
    • addedInput schema / properties / memory_type
      Added value: +{
      +  "description": "Which kinds of notes: one of context | fact | feedback | summary | procedural, or a list. Default 'context' (a call with `key` reads every type).",
      +  "items": {
      +    "enum": [
      +      "context",
      +      "fact",
      +      "feedback",
      +      "summary",
      +      "procedural"
      +    ],
      +    "type": "string"
      +  },
      +  "type": [
      +    "string",
      +    "array"
      +  ]
      +}
    • changedInput schema / properties / scope / description
      Previous value: -"Optional filter: global | thread | person. Omit for all scopes."New value: +"Optional filter: workspace | agent | thread | person ('global' = agent). Omit for all scopes."
    • changedInput schema / properties / scope / enum
      Previous value: -[
      -  "global",
      -  "thread",
      -  "person"
      -]New value: +[
      +  "workspace",
      +  "agent",
      +  "global",
      +  "thread",
      +  "person"
      +]
  2. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
      +  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
      +  "type": "integer"
      +}
  3. Added
  4. Removed
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds real value beyond that: cross-agent reads are read-only, in_workspace affects only this one call and stores nothing, and no other sessions are affected. It repeats "read-only" which annotations already imply, and says nothing about large-result behavior beyond the limit hint 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.

Conciseness4/5

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

Four sentences, each carrying distinct information, with the default behavior front-loaded before the override options. Minor redundancy: the default own-notes and newest-first behavior is restated from the schema, and the scope list partially duplicates the enum.

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 an 8-parameter, all-optional read tool with no output schema, the description covers the entry point, the default result semantics, the two most consequential filters, and the shape of each result (agent_id and agent_name). Numeric caps, format modes and memory_type selection are left entirely to the schema, but those are adequately documented there.

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?

With 100% schema description coverage the schema already documents key, limit, scope, format, memory_type, in_workspace, scope_ref_id and filter_agent_id in detail. The description largely restates those semantics (default own-notes, "all"/"*" behavior) rather than adding new interpretation, and its scope enumeration lists global/thread/person while omitting workspace/agent. Baseline 3 is right when the schema does the heavy lifting.

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

Purpose4/5

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

The description opens with a specific verb and resource ("Recall notes from your notebook") and immediately defines the default result set (own notes, all scopes, newest first). It is unambiguous about what comes back, but it never contrasts itself with notes_search or notes_delete, so an agent must infer which of the notes_* family to pick.

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 concrete operating instructions: omit filter_agent_id for your own notebook, pass a numeric id to read another agent's, pass "all"/"*" for workspace-wide, and pass scope to narrow. What is missing is exclusion guidance — when to use notes_search instead of this, or when reading across all agents is inappropriate.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.