Skip to main content
Glama

Remember

remember

Use when the user says what they are working on, states a preference, decision or fact they want kept for next time, or asks you to remember or keep something in mind. Store one durable fact per call. If recall already showed the same fact, do not save it again. Not for long documents: use publish_document for those. Team members: leaving scope out saves to that member's own private memory, which no other team member can read. Use scope "project" with a project_key to share with the team. If the fact comes from a Gryz document, pass it as a source so people can see where it came from.

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": {
      "body": "<body>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesAtomic fact to remember (1–4000 chars)
kindNoOptional coarse taxonomy — advisory, does not filter recall
scopeNoMemory scope. Optional, defaults to "personal" (the person's own memory). Use "project" with a project_key to share with a project.
sourcesNoOptional: the Gryz documents this fact comes from (at most 5). Only documents you can read in the same space as this memory. Gryz marks the fact when one of them changes or is deleted.
subjectNoOptional short noun phrase this fact is about (e.g. "editor theme"). Helps the nightly consolidation job group near-duplicates. Advisory only — never filters recall.
salienceNo
valid_fromNoWhen the fact became true (ISO timestamp)
project_keyNoRequired when scope is project

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only reveal that this is a non-idempotent, non-destructive write. The description adds the behaviors that actually matter: one fact per call, a duplicate-suppression rule keyed off recall, the privacy consequence of omitting scope, the sharing consequence of scope="project" with project_key, and source-provenance tracking.

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?

Front-loaded with the trigger condition, then constraints, then scope semantics — a sensible ordering with no filler sentences. It is dense, and the team-member/scope passage is long enough to slightly dilute the early guidance.

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 write tool with no output schema, the definition covers selection, dedup, privacy, and provenance well. It says nothing about what a successful save returns (an id, a created/updated status), which an agent would otherwise have to discover by calling.

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 already 88%, so the schema carries most parameter detail. The description still adds meaning the schema does not: that omitted scope writes to the member's private memory that no teammate can read, and that sources let people see where a fact came from. salience, valid_from, and kind are left entirely to 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?

"Store one durable fact per call" gives a specific verb (store) and resource (one durable fact), and the definition explicitly contrasts itself with publish_document and with recall de-duplication. An agent can select it without opening another schema.

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

Usage Guidelines5/5

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

It names the triggering situations (user states a preference, decision, fact, or asks you to remember), an explicit exclusion with an alternative (long documents → publish_document), a precondition tied to recall, and scope-choice guidance for private vs team memory.

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.