Artel

memory_write

Write facts, decisions, and plans to shared memory with tags and scopes so agents can retrieve them later.

Instructions

Write something to shared memory. Use this often.

Write whenever you learn, decide, or discover something worth keeping:

Facts about the codebase, infrastructure, or domain
Decisions made and why
Bugs found, workarounds, gotchas
Plans, designs, open questions
Anything another agent (or future you) would want to know

Types:

memory: default, use this for everything
doc: stable reference material; normally written by the archivist, not agents
directive: a standing instruction the archivist reads before synthesis; scoped like any entry, but the archivist loads directives from every project it can see, so write it to apply beyond this project too; confidence is always forced to 1.0 and it never decays
skill: procedural knowledge, how to do something; decays like memory, never promoted, never merged; superseded by directives on the same topic

Scopes:

project: visible to all members of this project (default)
agent: only you can see it

Args: content: What to store. Markdown is fine. entry_type: See types above. Default: memory. scope: See scopes above. Default: project. project: Project to scope the entry to. Defaults to MCP_PROJECT if set. tags: Tags for filtering and retrieval. Use them, they make memory_list useful. confidence: How certain you are (0.0–1.0). Default 1.0. Use lower for guesses.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No	Tags for filtering and retrieval. Use them, they make memory_list useful.
`scope`	No	See scopes above. Default: project.	project
`content`	Yes	What to store. Markdown is fine.
`project`	No	Project to scope the entry to. Defaults to MCP_PROJECT if set.
`confidence`	No	How certain you are (0.0–1.0). Default 1.0. Use lower for guesses.
`entry_type`	No	See types above. Default: memory.	memory

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.47.0Sep 24, 2026

changedInput schema / properties / tags / description

Previous value: -"Tags for filtering and retrieval. Use them — they make memory_list useful."New value: +"Tags for filtering and retrieval. Use them, they make memory_list useful."

Addedv0.17.0May 27, 2026
Removedv0.16.1May 21, 2026
Addedv0.9.0May 16, 2026
Removedv0.7.0May 15, 2026
First observedv0.1.0May 13, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With annotations only covering open-world and destructiveness hints, the description carries the transparency burden and does so well: it explains directive confidence forcing, decay behavior for skills, scoping rules, and the default project behavior. It reveals how different entry types behave after writing, which goes well beyond the minimal 'write an entry' statement.

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 description is longer than typical, but nearly every sentence earns its place given the complex entry-type system and scope rules. The use-case bullets and 'Types'/'Scopes' sections are well organized and front-loaded with the core intent before the details.

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?

Given that an output schema exists, return-value documentation is unnecessary, and the description covers all six parameters, their defaults, and the behavioral nuances of each entry type. An agent has enough information to call this tool correctly in a wide range of scenarios without needing to open sibling schemas.

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 100%, so the baseline is 3, but the description adds real value by explaining the semantics of entry_type (memory/doc/directive/skill lifecycle), scope visibility, confidence interpretation, and default project resolution. It also reinforces the tags guidance in a way that helps the agent use them more effectively.

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 opens with a clear verb-resource pair: 'Write something to shared memory,' immediately distinguishing it from read/update/delete/list siblings. The bulleted list of use cases (facts, decisions, bugs, plans, open questions) makes the tool's purpose concrete and actionable.

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

Usage Guidelines4/5

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

The description gives strong when-to-use guidance ('Use this often... Write whenever you learn, decide, or discover something worth keeping') and even states exclusions, such as doc entries being 'normally written by the archivist, not agents.' It does not explicitly name alternatives like memory_update for corrections, but the use cases and type-level guidance are clear enough for selection.

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