Skip to main content
Glama

Record how the user works

learn_about_user

Captures a specific, lasting observation about the user's preferences, patterns, or working style so assistants can recall and tailor future responses.

Instructions

Record something lasting about how the user thinks, writes, or works. category: thinking | voice | learning | working | taste | patterns | now. kind: prefers | dislikes | pattern | struggles | works | style | goal | fact. observation: one specific plain sentence, e.g. "Wants the blunt answer first, no sugar-coating". source: where it came from, e.g. "chat (correction)".

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "category": "<category>",
      "observation": "<observation>",
      "kind": "<kind>"
    },
    "name": "learn_about_user"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
sourceNochat
categoryYes
observationYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write, so the safety profile is covered. The description adds the useful durability signal ("lasting") but says nothing about duplicate handling, whether repeated identical observations create multiple entries (relevant given idempotentHint=false), or how conflicts with existing memories are resolved.

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?

The purpose sentence is front-loaded, followed by compact per-field guidance in a consistent category/kind/observation/source order. It is tight for a four-parameter tool, with only mild redundancy between the field labels and their examples.

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

Completeness3/5

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

Because an output schema exists, return values need no explanation, and the description adequately compensates for the empty schema coverage on parameters. What it omits is routing guidance against the overlapping memory siblings and any statement about deduplication, which matter for a non-idempotent write into a persistent user model.

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

Parameters4/5

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

Schema coverage is 0% and the schema carries no enums, so the description is doing real work: it enumerates the seven category values and eight kind values that the schema leaves as bare strings, and it illustrates observation and source with concrete examples. The gap is that it never states that source is optional or what happens with an unrecognized category/kind value.

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 states a specific verb and resource: "Record something lasting about how the user thinks, writes, or works." The word "lasting" distinguishes it from transient chat logging, and the field list narrows the domain to durable user-model facts. It does not name the nearest siblings (remember, note_user_voice, how_user_works), so the boundary is inferred rather than stated.

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?

Usage is implied by the examples and by "something lasting," which suggests durable observations rather than session notes. However, there is no explicit when-to-use, when-not-to-use, or pointer to the alternatives that clearly overlap (remember, note_user_voice, how_user_works). An agent must guess at the boundary between these memory tools.

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