Skip to main content
Glama

DeNasty Memory

Remember for this project

remember

Saves one memory for a project so every AI tool of this user sees it later. Use for decisions (and why), conventions, important context, open tasks. Keep it short and self-contained. Secrets are removed automatically.

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": {
      "project": "<project>",
      "kind": "<kind>",
      "title": "<title>",
      "body": "<body>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
kindYes
tagsNo
titleYes
projectYesProject or repository name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the key behavioral trait: the write is visible to all of the user's AI tools later, and secrets are scrubbed automatically — neither is expressible in the provided hints. It leaves unstated whether writing a duplicate creates a second memory (relevant given idempotentHint=false) and what handle, if any, comes back.

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?

Four short sentences ordered as purpose, usage, content guidance, and a safety caveat — front-loaded and free of filler. Nothing repeats the schema or the annotations verbatim to no effect.

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 a five-parameter write tool with no output schema and permissive annotations, the description covers purpose, triggers, content shape, and the sanitization caveat. Remaining gaps — tags, duplicate handling, and any return value — are modest but real given the low schema coverage.

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 coverage is only 20%, so the description carries most of the burden; it partially does by enumerating usable kinds (decision, convention, context, todo — omitting note) and implying the title/body should be short and self-contained. Top-level 'tags' (up to 10) is never mentioned, and no length or format guidance is added for title or body.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Saves one memory for a project so every AI tool of this user sees it later" gives a specific verb (saves), resource (memory), cardinality (one), and scope (per project, shared across the user's tools). It is clearly distinct from project_brief or list_projects in intent, though it never names a sibling such as recall or forget to sharpen the boundary.

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 second sentence gives concrete when-to-use triggers: decisions (and their rationale), conventions, important context, open tasks. It does not state when NOT to use it (e.g., ephemeral notes, or reading existing memories via recall), so the exclusion side is inferred rather than stated.

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.

Resources