brain

Overview Schema Source Related Servers Discussions Admin

add_memory

Saves a durable user fact to a categorized memory file with date, preventing duplicates. Supersedes older facts, keeping them in history.

Instructions

Guarda un hecho duradero sobre el usuario en memory/.md (sin duplicar), con la fecha en que se guardó. Ej: add_memory("Prefiere respuestas cortas", "Preferencias"). Si este hecho reemplaza a uno anterior (cambió de dirección, de trabajo, etc.), pasá el texto del hecho viejo en supersede — no se borra, queda marcado como superado con fecha en el mismo archivo (sección ## Historial).

Input Schema

TableJSON Schema

Name	Required	Default
`fact`	Yes
`category`	No	General
`supersede`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.1Sep 30, 2026

addedInput schema / properties / supersede

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Supersede"
+}

First observedv0.1.0Sep 26, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the destination path, that duplicates are avoided, that a save date is attached, and that superseded facts are not deleted but marked with date under ## Historial. Missing only auth/permission prerequisites and error behavior, which leaves a small gap.

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?

Front-loads the core action and path, then the example, then the supersede rule. Every sentence adds value, though the supersede clause is somewhat dense and could be split for readability.

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 mutation tool with an output schema (so return values need not be described) and no annotations, the description covers storage location, dedup, dating, and supersede behavior. It is nearly complete, lacking only permission or failure-mode context.

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 0%, so the description must compensate; it explains `supersede` semantics thoroughly (pass the old fact text, marked not deleted, stored in Historial) and contextualizes `category` via the path and example. `fact` is self-evident by name, though the category default ('General') and valid range are not stated.

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?

States a specific verb (Guarda) and resource (un hecho duradero sobre el usuario) plus the storage target (memory/<category>.md), which distinguishes it from siblings like memory_history or write_file. The inline example makes the intent unambiguous.

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?

Gives a concrete usage example and, importantly, a conditional rule: use `supersede` when the new fact replaces an old one (changed address, job, etc.). It doesn't name sibling alternatives or state when NOT to use it, but the when-to-use guidance for the core parameter is explicit.

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