Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Remember

remember

Store one durable rule, style, preference, fact, or project decision about a user or repository so later conversations on any device can recall it. Use one sentence per call to keep context consistent.

Instructions

Remember one thing about the user for later conversations, on every device: a standing rule for a repository, their code or writing style, how they like to work, a fact about them or their team, or what they built or decided. One thing per call, as a plain sentence under 500 characters that still makes sense months from now. kind: rule, style, preference, fact or project. Give repo as owner/repo only for a memory about one repository. Text close to a memory the user already has is refused with memory_similar, which names that memory: call update_memory on it when it is the same thing, or remember again with keep_both true when it is a different thing. When memory is on_request, save only what the user asks you to remember. Refused with memory_off when memory is off. Never keys, tokens, passwords or other secrets.

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

Input Schema

NameRequiredDescriptionDefault
kindYes
repoNo
textYes
keep_bothNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing refusal behavior and its error codes, the duplicate-detection flow, the on_request saving policy, the memory_off state, the 500-character/one-fact constraint, and a safety prohibition on secrets. Nothing here contradicts readOnlyHint=false, destructiveHint=false, openWorldHint=true or idempotentHint=false.

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?

Purpose and constraints are front-loaded and every sentence carries information. The middle section is a dense run-on covering duplicate handling, modes and refusal codes, which makes it harder to scan than it could be, but no sentence is filler.

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

Completeness5/5

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

For a four-parameter write tool with no output schema, the description covers all parameters, the success constraint, the duplicate path, the two refusal states and the secrets prohibition. An agent has everything needed to call it correctly and interpret failures.

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

Parameters5/5

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

Schema description coverage is 0%, but the description compensates fully: it defines text (one plain sentence under 500 characters that still makes sense months from now), enumerates the kind enum values, explains repo as owner/repo and only for repository-specific memories, and gives keep_both its operational meaning.

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?

Opens with a specific verb and resource ('Remember one thing about the user for later conversations, on every device') and immediately enumerates the kinds of content it accepts. It is clearly distinguishable from update_memory, forget_memory, list_memories and search_memory, which the description names or implies.

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?

Explicitly routes the agent: when text is close to an existing memory, call update_memory if it is the same thing, or call remember again with keep_both true if it is a different thing. It also states the mode-conditional rule ('when memory is on_request, save only what the user asks') and names the failure modes memory_similar and memory_off.

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