Renor

remember_fact

Stores or supersedes durable facts about a subject and predicate, closing the prior current value and returning a receipt so agents can recall context across sessions.

Instructions

Durable memory write: stores (or supersedes) a fact about a subject. Ledger-first (survives index rebuild), temporal (closes the previous current fact for that subject+predicate). Returns a receipt. Use for "remember that…" statements. Confidence is not representable in the ledger.

Input Schema

Name	Required	Description
`object`	Yes	The current value, e.g. "Memory Company". A single string: pass a list or a struct as ONE joined string, never as JSON or an array.
`source`	No	Ignored. The author is this connection's header-form name. When the connection has no usable name, the engine default (agent) is stored. Never a file path or document name.
`subject`	Yes	Who or what the fact is about, e.g. "Renor". A single string, not a nested object.
`predicate`	Yes	The relation or attribute being asserted, e.g. "works_at". A short single-line string.

Output Schema

Name	Required	Description	Default
`action`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.3.0Oct 29, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": {},
+  "properties": {
+    "action": {
+      "enum": [
+        "supersede",
+        "store",
+        "nochange"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "action"
+  ],
+  "type": "object"
+}

First observedv1.2.0Oct 28, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses ledger-first durability, temporal supersession that closes the previous current fact, that it returns a receipt, and that confidence is not representable. It does not cover permissions, rate limits, or exact reversal behavior, which prevents a top score.

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 description is compact and front-loaded: it begins with the core operation, then layers in durability, temporal behavior, return behavior, and usage trigger. Every sentence adds information without repetition.

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?

An output schema exists, so omitting receipt details is acceptable, and the description sufficiently explains the write model, supersession, and usage trigger. It leaves some operational context unexplained, such as authorization or duplicate-handling nuances, but is complete enough to call correctly.

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 the parameter fields are already fully documented by the schema. The description adds useful semantics around subject+predicate temporal supersession and the fact that confidence cannot be stored, but it does not add syntax or format detail beyond the schema.

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?

The description states a specific verb and resource: a durable memory write that stores or supersedes a fact about a subject. It distinguishes itself from read-oriented siblings like facts and search by framing the operation as a write, though it does not explicitly name the sibling alternatives.

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?

It gives a clear trigger phrase, 'Use for "remember that…" statements,' which helps the agent recognize when to invoke it. It does not explicitly state when not to use it or compare it with sibling tools such as note or evidence.

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

Deploy Server