mnemolith

Overview Schema Source Related Servers Discussions Admin

remember

Save durable project facts so future AI sessions in any tool know conventions, setup gotchas, and decisions; link facts to dependent files so stale notes are flagged when those files change.

Instructions

Save a durable fact about this project so future sessions, in any AI tool, know it. Use this, not a built-in memory or notes file, whenever the user asks you to remember something about the project.

Good facts: conventions ("we use pnpm, not npm"), setup gotchas ("tests need DOCKER_HOST set"),
decisions and their reasons. Not: temporary task details or anything in the code already.
files: repo-relative paths this fact depends on (e.g. ["docker-compose.yml"]), so the memory
can be flagged when those files change.
replaces: the id of a memory this fact makes untrue (e.g. "m42"), to save and retire it in one call.

Input Schema

Name	Required	Description	Default
`fact`	Yes
`files`	No
`replaces`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.4Nov 6, 2026
- addedInput schema / properties / replaces
```
Added value: +{
+  "default": "",
+  "title": "Replaces",
+  "type": "string"
+}
```
First observedOct 17, 2026

TDQS

A4.8/5.0

Behavior4/5

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

With no annotations, the description bears the full burden of behavioral disclosure. It explains the operational implications of the `files` parameter (flagging when changed) and the `replaces` parameter (retiring old memories).

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?

The information is well-structured, moving from the high-level purpose to usage guidelines and then drilling down into specific parameter semantics. No sentence is wasted, and the scope definition is front-loaded.

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?

The tool is complex due to its metadata requirements (`files`, `replaces`). The description covers all necessary context for an agent to choose this tool over siblings and invoke it with correct semantics.

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?

Since schema description coverage is 0%, the description must compensate. It perfectly explains the semantic meaning of all three parameters, detailing what 'files' means (repo-relative paths) and what 'replaces' refers to (memory ID).

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?

The description clearly states the goal: to save a 'durable fact' for future sessions and distinguishes this function from built-in memory or notes files.

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 provides explicit guidelines on when to use the tool (conventions, setup gotchas, decisions) and, critically, when *not* to use it (temporary task details or code content).

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

Deploy Server