Skip to main content
Glama

remember

Store decisions, facts, preferences, and completed or pending tasks so every AI coding tool can recall shared context.

Instructions

Store an important memory (decision, fact, user preference, completed/pending task) so every tool remembers it.

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": {
      "kind": "<kind>",
      "content": "<content>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesMemory type: decision, fact, preference, open task (task_pending), finished task (task_done), fixed error (error_fixed) or general context
contentYesMemory content, short and dense
projectNoOptional — project path or name; omit for a global memory
importanceNo0 to 1; higher ranks first in context

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.16.1
    • addedInput schema / properties / importance / description
      Added value: +"0 to 1; higher ranks first in context"
    • addedInput schema / properties / kind / description
      Added value: +"Memory type: decision, fact, preference, open task (task_pending), finished task (task_done), fixed error (error_fixed) or general context"
    • changedInput schema / properties / project / description
      Previous value: -"Path proyek (opsional)"New value: +"Optional — project path or name; omit for a global memory"
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden; it does disclose one real behavioral trait, that stored memories become visible to every tool rather than being local. It says nothing about deduplication, overwriting, conflict handling, or persistence scope (project vs global), which matter for a write tool with zero annotation coverage.

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?

One sentence with the verb and resource front-loaded and the qualifying examples inline; nothing is padded or repeated.

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?

Adequate for a four-parameter write tool whose schema is fully documented, but with no annotations and no output schema the description should cover more of the write contract, such as whether repeated identical content creates duplicates and how project versus global scope behaves.

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 kind, content, project, and importance are already documented with enum values and defaults. The description's parenthetical list of memory types partially mirrors the kind enum but adds no syntax, format, or sizing guidance beyond the schema.

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?

States a specific verb (store) and resource (memory), and parenthesizes the kinds of content it captures (decision, fact, preference, task). An agent can distinguish it from retrieval siblings like recall or get_memory, though the description never names those siblings directly.

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?

"important memory" gives an implied threshold for when to call it, but there is no explicit when-not guidance (e.g., don't use for transient context, use update_memory for existing entries) and no named alternative among the siblings.

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