Skip to main content
Glama

remember

File a concept, decision, or finding as a memory node. Search first to prevent duplicates; review suggested connections after creation.

Instructions

File a concept, decision, or finding. Use this for a single entry only — prefer remember_all for batches — and always search first to avoid creating a duplicate. Before filing, consider whether a similar memory already exists. If so, suggest linking to it with connect rather than creating a duplicate. Duplicate nodes with no edges are the most common cause of drift candidates. Use transient=true for ticket state, sprint notes, or any node expected to become stale within days. Transient nodes are candidates for archiving once the related work is complete. The response includes a suggested_connections field — review these and call connect for any that are relevant.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
descriptionNoWhat this node is about
domainYesThe domain or project this belongs to (e.g. 'deep-game', 'sedex', 'general')
labelYesShort name for this node (e.g. 'RST $10 boot crash')
occurred_atNoOptional ISO8601 date or datetime when this event or decision actually happened (e.g. '2026-04-01' or '2026-04-01T14:30:00Z'). Distinct from when it was filed.
related_toNoOptional list of nodes to auto-connect at creation time. Each item is either a plain node ID string (creates a connects_to edge) or an object with id and relationship fields. Invalid or unknown IDs are silently skipped.
tagsNoSpace-separated synonyms and keywords that improve search recall. Examples: 'testing gradle kotlin approval'. These are searched alongside label, description, and why_matters. Populate this with alternative terms an agent might use to find this node later.
transientNoSet to true for short-lived knowledge: ticket state, sprint notes, or anything expected to become stale within days. Transient nodes older than 7 days are surfaced by whats_stale as archiving candidates.
why_mattersNoWhy this is significant - the 'so what'
Behavior4/5

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

With no annotations, the description carries full burden. It discloses behavioral traits: duplicate nodes cause drift candidates, transient nodes become archiving candidates after 7 days, and the response includes suggested_connections for review. Missing details on permissions or error handling but overall transparent.

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 front-loaded with the core purpose and then provides guidelines and behavioral notes. It is slightly verbose but each sentence adds value. Could be more concise without losing meaning.

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?

Given the tool has 8 parameters and no output schema, the description covers purpose, usage, behavioral traits, and mentions the suggested_connections response field. It adequately helps an agent decide when and how to use the tool.

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 baseline is 3. The description adds marginal context (e.g., 'Short name' for label, 'alternative terms' for tags) but does not significantly exceed what the schema already provides. It explains the why for tags but not all parameters.

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 tool files a 'concept, decision, or finding' and explicitly distinguishes from the sibling 'remember_all' by specifying this is for a single entry only. The verb 'file' is specific, and the resource is well-defined.

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?

Provides explicit when-to-use (single entry), when-not (batches to remember_all), and mandatory prerequisite (search first to avoid duplicates). Also advises using transient=true for temporary data and suggests connecting rather than duplicating, offering clear alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/corbym/memoryweb'

If you have feedback or need assistance with the MCP directory API, please join our Discord server