Persistent Project Context for xAI Grok

Portable structured memory (.fafm)

faf_memory

Read-onlyIdempotent

Phase III (FRC) — query the durable .fafm model by type/tag/priority/text. Omit filters for a structured summary. .fafm is NOT scored: this SELECTS facts (provenance preserved), never grades them.

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": {
      "content": "<content>"
    },
    "name": "faf_memory"
  }
}

Input Schema

Name	Required	Description
`tag`	No	Filter by a tag.
`type`	No	Filter by fact type (e.g. "feedback").
`query`	No	Case-insensitive substring match on fact text.
`content`	Yes	Raw .fafm YAML content.
`priority`	No	Filter by priority (e.g. "critical").

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 9, 2026

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "content": {
-      "items": {
-        "properties": {
-          "text": {
-            "description": "Human-readable tool result.",
-            "type": "string"
-          },
-          "type": {
-            "const": "text",
-            "type": "string"
-          }
-        },
-        "required": [
-          "type",
-          "text"
-        ],
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "isError": {
-      "description": "True when the tool failed.",
-      "type": "boolean"
-    }
-  },
-  "required": [
-    "content",
-    "isError"
-  ],
-  "type": "object"
-}New value: +null

Changed1 schema field changedJul 4, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "content": {
+      "items": {
+        "properties": {
+          "text": {
+            "description": "Human-readable tool result.",
+            "type": "string"
+          },
+          "type": {
+            "const": "text",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "isError": {
+      "description": "True when the tool failed.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "content",
+    "isError"
+  ],
+  "type": "object"
+}

AddedJun 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds meaningful behavior context: the durable select preserves provenance, omitting filters yields a summary, and the tool never grades or modifies facts. This goes well beyond the annotations.

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?

Two compact sentences, both functioning and non-duplicated. The primary action is front-loaded, and the distinguishing 'never grades' warning is placed at the end for emphasis without padding.

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 filtered query tool, the description covers what it operates on, how to filter, and what happens if filters are omitted. It is not entirely explicit about the exact shape or fields of the returned structured summary, but the core decision and invocation knowledge is present.

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 description coverage is 100%, so the baseline is 3. The description adds an important cross-parameter semantic: omitting all filters produces a structured summary rather than a filtered list. It also summarizes the query axes as type/tag/priority/text, reinforcing how the optional filters work together.

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 ('query') with a specific resource (the durable .fafm model) and the filter dimensions (type/tag/priority/text). It also explicitly differentiates itself from grading tools by saying it selects facts and never grades them, which is enough to distinguish it from faf_score and faf_analyze.

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?

Provides a clear usage rule: 'Omit filters for a structured summary.' It implies this is the read/query choice for fafm content, and the 'never grades them' clause tells the agent this is not for scoring. It does not name an alternative explicitly, so it falls just short of a 5.

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

All Persistent Project Context for xAI Grok tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.